The best NLP papers of 2014
The best NLP papers of 2014 include "Neural Machine Translation by Jointly Learning to Align and Translate", "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation", "Sequence to Sequence Learning with Neural Networks", "Convolutional Neural Networks for Sentence Classification", and "Distributed Representations of Sentences and Documents". These papers cover topics such as machine translation, sentence representation, sequence learning, and sentence classification.
1. Neural Machine Translation by Jointly Learning to Align and Translate
25 422 citations
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.
2. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
21 034 citations
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.
3. Sequence to Sequence Learning with Neural Networks
19 101 citations
Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
4. Convolutional Neural Networks for Sentence Classification
12 712 citations
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.
5. Distributed Representations of Sentences and Documents
8 772 citations
Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the ordering of the words and they also ignore semantics of the words. For example, "powerful," "strong" and "Paris" are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents. Our algorithm represents each document by a dense vector which is trained to predict words in the document. Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models. Empirical results show that Paragraph Vectors outperform bag-of-words models as well as other techniques for text representations. Finally, we achieve new state-of-the-art results on several text classification and sentiment analysis tasks.
6. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
6 220 citations
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder--Decoder and a newly proposed gated recursive convolutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically.
7. CIDEr: Consensus-based Image Description Evaluation
3 723 citations
Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is renewed interest in this area. However, evaluating the quality of descriptions has proven to be challenging. We propose a novel paradigm for evaluating image descriptions that uses human consensus. This paradigm consists of three main parts: a new triplet-based method of collecting human annotations to measure consensus, a new automated metric (CIDEr) that captures consensus, and two new datasets: PASCAL-50S and ABSTRACT-50S that contain 50 sentences describing each image. Our simple metric captures human judgment of consensus better than existing metrics across sentences generated by various sources. We also evaluate five state-of-the-art image description approaches using this new protocol and provide a benchmark for future comparisons. A version of CIDEr named CIDEr-D is available as a part of MS COCO evaluation server to enable systematic evaluation and benchmarking.
8. A Convolutional Neural Network for Modelling Sentences
3 459 citations
The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The network uses Dynamic k-Max Pooling, a global pooling operation over linear sequences. The network handles input sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. The network does not rely on a parse tree and is easily applicable to any language. We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with respect to the strongest baseline.
9. Embedding Entities and Relations for Learning and Inference in Knowledge Bases
2 678 citations
We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functions. Under this framework, we compare a variety of embedding models on the link prediction task. We show that a simple bilinear formulation achieves new state-of-the-art results for the task (achieving a top-10 accuracy of 73.2% vs. 54.7% by TransE on Freebase). Furthermore, we introduce a novel approach that utilizes the learned relation embeddings to mine logical rules such as "BornInCity(a,b) and CityInCountry(b,c) => Nationality(a,c)". We find that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication. More interestingly, we demonstrate that our embedding-based rule extraction approach successfully outperforms a state-of-the-art confidence-based rule mining approach in mining Horn rules that involve compositional reasoning.
10. Deep Speech: Scaling up end-to-end speech recognition
1 976 citations
We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.
11. Memory Networks
1 632 citations
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in the context of question answering (QA) where the long-term memory effectively acts as a (dynamic) knowledge base, and the output is a textual response. We evaluate them on a large-scale QA task, and a smaller, but more complex, toy task generated from a simulated world. In the latter, we show the reasoning power of such models by chaining multiple supporting sentences to answer questions that require understanding the intension of verbs.
12. Collaborative Deep Learning for Recommender Systems
1 538 citations
Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. However, the ratings are often very sparse in many applications, causing CF-based methods to degrade significantly in their recommendation performance. To address this sparsity problem, auxiliary information such as item content information may be utilized. Collaborative topic regression (CTR) is an appealing recent method taking this approach which tightly couples the two components that learn from two different sources of information. Nevertheless, the latent representation learned by CTR may not be very effective when the auxiliary information is very sparse. To address this problem, we generalize recent advances in deep learning from i.i.d. input to non-i.i.d. (CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix. Extensive experiments on three real-world datasets from different domains show that CDL can significantly advance the state of the art.
13. word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
1 534 citations
The word2vec software of Tomas Mikolov and colleagues (https://code.google.com/p/word2vec/ ) has gained a lot of traction lately, and provides state-of-the-art word embeddings. The learning models behind the software are described in two research papers. We found the description of the models in these papers to be somewhat cryptic and hard to follow. While the motivations and presentation may be obvious to the neural-networks language-modeling crowd, we had to struggle quite a bit to figure out the rationale behind the equations. This note is an attempt to explain equation (4) (negative sampling) in "Distributed Representations of Words and Phrases and their Compositionality" by Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado and Jeffrey Dean.
14. Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
1 341 citations
Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images and sentences while the decoder can generate novel descriptions from scratch. Using LSTM to encode sentences, we match the state-of-the-art performance on Flickr8K and Flickr30K without using object detections. We also set new best results when using the 19-layer Oxford convolutional network. Furthermore we show that with linear encoders, the learned embedding space captures multimodal regularities in terms of vector space arithmetic e.g. *image of a blue car* - "blue" + "red" is near images of red cars. Sample captions generated for 800 images are made available for comparison.
15. From Captions to Visual Concepts and Back
1 261 citations
This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to train visual detectors for words that commonly occur in captions, including many different parts of speech such as nouns, verbs, and adjectives. The word detector outputs serve as conditional inputs to a maximum-entropy language model. The language model learns from a set of over 400,000 image descriptions to capture the statistics of word usage. We capture global semantics by re-ranking caption candidates using sentence-level features and a deep multimodal similarity model. Our system is state-of-the-art on the official Microsoft COCO benchmark, producing a BLEU-4 score of 29.1%. When human judges compare the system captions to ones written by other people on our held-out test set, the system captions have equal or better quality 34% of the time.
16. SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation
1 243 citations
We present SimLex-999, a gold standard resource for evaluating distributional semantic models that improves on existing resources in several important ways. First, in contrast to gold standards such as WordSim-353 and MEN, it explicitly quantifies similarity rather than association or relatedness, so that pairs of entities that are associated but not actually similar [Freud, psychology] have a low rating. We show that, via this focus on similarity, SimLex-999 incentivizes the development of models with a different, and arguably wider range of applications than those which reflect conceptual association. Second, SimLex-999 contains a range of concrete and abstract adjective, noun and verb pairs, together with an independent rating of concreteness and (free) association strength for each pair. This diversity enables fine-grained analyses of the performance of models on concepts of different types, and consequently greater insight into how architectures can be improved. Further, unlike existing gold standard evaluations, for which automatic approaches have reached or surpassed the inter-annotator agreement ceiling, state-of-the-art models perform well below this ceiling on SimLex-999. There is therefore plenty of scope for SimLex-999 to quantify future improvements to distributional semantic models, guiding the development of the next generation of representation-learning architectures.
17. Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
1 188 citations
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. It directly models the probability distribution of generating a word given previous words and an image. Image captions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on four benchmark datasets (IAPR TC-12, Flickr 8K, Flickr 30K and MS COCO). Our model outperforms the state-of-the-art methods. In addition, we apply the m-RNN model to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval. The project page of this work is: www.stat.ucla.edu/~junhua.mao/m-RNN.html .
18. On Using Very Large Target Vocabulary for Neural Machine Translation
970 citations
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent success, neural machine translation has its limitation in handling a larger vocabulary, as training complexity as well as decoding complexity increase proportionally to the number of target words. In this paper, we propose a method that allows us to use a very large target vocabulary without increasing training complexity, based on importance sampling. We show that decoding can be efficiently done even with the model having a very large target vocabulary by selecting only a small subset of the whole target vocabulary. The models trained by the proposed approach are empirically found to outperform the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models. Furthermore, when we use the ensemble of a few models with very large target vocabularies, we achieve the state-of-the-art translation performance (measured by BLEU) on the English->German translation and almost as high performance as state-of-the-art English->French translation system.
19. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
967 citations
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully used for sequence labeling and sequence prediction tasks, such as handwriting recognition, language modeling, phonetic labeling of acoustic frames. However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in small scale tasks. In this paper, we present novel LSTM based RNN architectures which make more effective use of model parameters to train acoustic models for large vocabulary speech recognition. We train and compare LSTM, RNN and DNN models at various numbers of parameters and configurations. We show that LSTM models converge quickly and give state of the art speech recognition performance for relatively small sized models.
20. Translating Videos to Natural Language Using Deep Recurrent Neural Networks
929 citations
Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal with recent breakthroughs in deep learning for natural language grounding in static images. In this paper, we propose to translate videos directly to sentences using a unified deep neural network with both convolutional and recurrent structure. Described video datasets are scarce, and most existing methods have been applied to toy domains with a small vocabulary of possible words. By transferring knowledge from 1.2M+ images with category labels and 100,000+ images with captions, our method is able to create sentence descriptions of open-domain videos with large vocabularies. We compare our approach with recent work using language generation metrics, subject, verb, and object prediction accuracy, and a human evaluation.
21. Grammar as a Foreign Language
913 citations
Syntactic constituency parsing is a fundamental problem in natural language processing and has been the subject of intensive research and engineering for decades. As a result, the most accurate parsers are domain specific, complex, and inefficient. In this paper we show that the domain agnostic attention-enhanced sequence-to-sequence model achieves state-of-the-art results on the most widely used syntactic constituency parsing dataset, when trained on a large synthetic corpus that was annotated using existing parsers. It also matches the performance of standard parsers when trained only on a small human-annotated dataset, which shows that this model is highly data-efficient, in contrast to sequence-to-sequence models without the attention mechanism. Our parser is also fast, processing over a hundred sentences per second with an unoptimized CPU implementation.
22. Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
892 citations
We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our model works on a finer level and embeds fragments of images (objects) and fragments of sentences (typed dependency tree relations) into a common space. In addition to a ranking objective seen in previous work, this allows us to add a new fragment alignment objective that learns to directly associate these fragments across modalities. Extensive experimental evaluation shows that reasoning on both the global level of images and sentences and the finer level of their respective fragments significantly improves performance on image-sentence retrieval tasks. Additionally, our model provides interpretable predictions since the inferred inter-modal fragment alignment is explicit.
23. Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
863 citations
Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word vectors as input as is often done, we directly apply CNN to high-dimensional text data, which leads to directly learning embedding of small text regions for use in classification. In addition to a straightforward adaptation of CNN from image to text, a simple but new variation which employs bag-of-word conversion in the convolution layer is proposed. An extension to combine multiple convolution layers is also explored for higher accuracy. The experiments demonstrate the effectiveness of our approach in comparison with state-of-the-art methods.
24. word2vec Parameter Learning Explained
772 citations
The word2vec model and application by Mikolov et al. have attracted a great amount of attention in recent two years. The vector representations of words learned by word2vec models have been shown to carry semantic meanings and are useful in various NLP tasks. As an increasing number of researchers would like to experiment with word2vec or similar techniques, I notice that there lacks a material that comprehensively explains the parameter learning process of word embedding models in details, thus preventing researchers that are non-experts in neural networks from understanding the working mechanism of such models. This note provides detailed derivations and explanations of the parameter update equations of the word2vec models, including the original continuous bag-of-word (CBOW) and skip-gram (SG) models, as well as advanced optimization techniques, including hierarchical softmax and negative sampling. Intuitive interpretations of the gradient equations are also provided alongside mathematical derivations. In the appendix, a review on the basics of neuron networks and backpropagation is provided. I also created an interactive demo, wevi, to facilitate the intuitive understanding of the model.
25. Addressing the Rare Word Problem in Neural Machine Translation
749 citations
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in conventional NMT systems is their inability to correctly translate very rare words: end-to-end NMTs tend to have relatively small vocabularies with a single unk symbol that represents every possible out-of-vocabulary (OOV) word. In this paper, we propose and implement an effective technique to address this problem. We train an NMT system on data that is augmented by the output of a word alignment algorithm, allowing the NMT system to emit, for each OOV word in the target sentence, the position of its corresponding word in the source sentence. This information is later utilized in a post-processing step that translates every OOV word using a dictionary. Our experiments on the WMT14 English to French translation task show that this method provides a substantial improvement of up to 2.8 BLEU points over an equivalent NMT system that does not use this technique. With 37.5 BLEU points, our NMT system is the first to surpass the best result achieved on a WMT14 contest task.
26. Question Answering with Subgraph Embeddings
690 citations
This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few hand-crafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers. Training our system using pairs of questions and structured representations of their answers, and pairs of question paraphrases, yields competitive results on a competitive benchmark of the literature.
27. A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
658 citations
We propose a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision. We combine discrete reasoning with uncertain predictions by a multi-world approach that represents uncertainty about the perceived world in a bayesian framework. Our approach can handle human questions of high complexity about realistic scenes and replies with range of answer like counts, object classes, instances and lists of them. The system is directly trained from question-answer pairs. We establish a first benchmark for this task that can be seen as a modern attempt at a visual turing test.
28. Statistically Significant Detection of Linguistic Change
441 citations
We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words. Such linguistic shifts are especially prevalent on the Internet, where the rapid exchange of ideas can quickly change a word's meaning. Our meta-analysis approach constructs property time series of word usage, and then uses statistically sound change point detection algorithms to identify significant linguistic shifts. We consider and analyze three approaches of increasing complexity to generate such linguistic property time series, the culmination of which uses distributional characteristics inferred from word co-occurrences. Using recently proposed deep neural language models, we first train vector representations of words for each time period. Second, we warp the vector spaces into one unified coordinate system. Finally, we construct a distance-based distributional time series for each word to track it's linguistic displacement over time. We demonstrate that our approach is scalable by tracking linguistic change across years of micro-blogging using Twitter, a decade of product reviews using a corpus of movie reviews from Amazon, and a century of written books using the Google Book-ngrams. Our analysis reveals interesting patterns of language usage change commensurate with each medium.
29. Wikipedia-based Semantic Interpretation for Natural Language Processing
422 citations
Adequate representation of natural language semantics requires access to vast amounts of common sense and domain-specific world knowledge. Prior work in the field was based on purely statistical techniques that did not make use of background knowledge, on limited lexicographic knowledge bases such as WordNet, or on huge manual efforts such as the CYC project. Here we propose a novel method, called Explicit Semantic Analysis (ESA), for fine-grained semantic interpretation of unrestricted natural language texts. Our method represents meaning in a high-dimensional space of concepts derived from Wikipedia, the largest encyclopedia in existence. We explicitly represent the meaning of any text in terms of Wikipedia-based concepts. We evaluate the effectiveness of our method on text categorization and on computing the degree of semantic relatedness between fragments of natural language text. Using ESA results in significant improvements over the previous state of the art in both tasks. Importantly, due to the use of natural concepts, the ESA model is easy to explain to human users.
30. Comparing and Combining Sentiment Analysis Methods
411 citations
Several messages express opinions about events, products, and services, political views or even their author's emotional state and mood. Sentiment analysis has been used in several applications including analysis of the repercussions of events in social networks, analysis of opinions about products and services, and simply to better understand aspects of social communication in Online Social Networks (OSNs). There are multiple methods for measuring sentiments, including lexical-based approaches and supervised machine learning methods. Despite the wide use and popularity of some methods, it is unclear which method is better for identifying the polarity (i.e., positive or negative) of a message as the current literature does not provide a method of comparison among existing methods. Such a comparison is crucial for understanding the potential limitations, advantages, and disadvantages of popular methods in analyzing the content of OSNs messages. Our study aims at filling this gap by presenting comparisons of eight popular sentiment analysis methods in terms of coverage (i.e., the fraction of messages whose sentiment is identified) and agreement (i.e., the fraction of identified sentiments that are in tune with ground truth). We develop a new method that combines existing approaches, providing the best coverage results and competitive agreement. We also present a free Web service called iFeel, which provides an open API for accessing and comparing results across different sentiment methods for a given text.
31. A Review of Verbal and Non-Verbal Human-Robot Interactive Communication
405 citations
In this paper, an overview of human-robot interactive communication is presented, covering verbal as well as non-verbal aspects of human-robot interaction. Following a historical introduction, and motivation towards fluid human-robot communication, ten desiderata are proposed, which provide an organizational axis both of recent as well as of future research on human-robot communication. Then, the ten desiderata are examined in detail, culminating to a unifying discussion, and a forward-looking conclusion.
32. Deep Learning for Answer Sentence Selection
405 citations
Answer sentence selection is the task of identifying sentences that contain the answer to a given question. This is an important problem in its own right as well as in the larger context of open domain question answering. We propose a novel approach to solving this task via means of distributed representations, and learn to match questions with answers by considering their semantic encoding. This contrasts prior work on this task, which typically relies on classifiers with large numbers of hand-crafted syntactic and semantic features and various external resources. Our approach does not require any feature engineering nor does it involve specialist linguistic data, making this model easily applicable to a wide range of domains and languages. Experimental results on a standard benchmark dataset from TREC demonstrate that---despite its simplicity---our model matches state of the art performance on the answer sentence selection task.
33. BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
387 citations
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-aligned data. This is achieved using a novel sampled bag-of-words cross-lingual objective, which is used to regularize two noise-contrastive language models for efficient cross-lingual feature learning. We show that bilingual embeddings learned using the proposed model outperform state-of-the-art methods on a cross-lingual document classification task as well as a lexical translation task on WMT11 data.
34. Explain Images with Multimodal Recurrent Neural Networks
372 citations
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on three benchmark datasets (IAPR TC-12, Flickr 8K, and Flickr 30K). Our model outperforms the state-of-the-art generative method. In addition, the m-RNN model can be applied to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.
35. Improving zero-shot learning by mitigating the hubness problem
368 citations
The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels. We show that the neighbourhoods of the mapped elements are strongly polluted by hubs, vectors that tend to be near a high proportion of items, pushing their correct labels down the neighbour list. After illustrating the problem empirically, we propose a simple method to correct it by taking the proximity distribution of potential neighbours across many mapped vectors into account. We show that this correction leads to consistent improvements in realistic zero-shot experiments in the cross-lingual, image labeling and image retrieval domains.
36. Word Representations via Gaussian Embedding
363 citations
Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its relationships, expressing asymmetries more naturally than dot product or cosine similarity, and enabling more expressive parameterization of decision boundaries. This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We compare performance on various word embedding benchmarks, investigate the ability of these embeddings to model entailment and other asymmetric relationships, and explore novel properties of the representation.
37. Analysis of Named Entity Recognition and Linking for Tweets
361 citations
Applying natural language processing for mining and intelligent information access to tweets (a form of microblog) is a challenging, emerging research area. Unlike carefully authored news text and other longer content, tweets pose a number of new challenges, due to their short, noisy, context-dependent, and dynamic nature. Information extraction from tweets is typically performed in a pipeline, comprising consecutive stages of language identification, tokenisation, part-of-speech tagging, named entity recognition and entity disambiguation (e.g. with respect to DBpedia). In this work, we describe a new Twitter entity disambiguation dataset, and conduct an empirical analysis of named entity recognition and disambiguation, investigating how robust a number of state-of-the-art systems are on such noisy texts, what the main sources of error are, and which problems should be further investigated to improve the state of the art.
38. An Autoencoder Approach to Learning Bilingual Word Representations
334 citations
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are aligned between two languages, while not relying on word-level alignments. We show that by simply learning to reconstruct the bag-of-words representations of aligned sentences, within and between languages, we can in fact learn high-quality representations and do without word alignments. Since training autoencoders on word observations presents certain computational issues, we propose and compare different variations adapted to this setting. We also propose an explicit correlation maximizing regularizer that leads to significant improvement in the performance. We empirically investigate the success of our approach on the problem of cross-language test classification, where a classifier trained on a given language (e.g., English) must learn to generalize to a different language (e.g., German). These experiments demonstrate that our approaches are competitive with the state-of-the-art, achieving up to 10-14 percentage point improvements over the best reported results on this task.
39. Open Question Answering with Weakly Supervised Embedding Models
329 citations
Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners. In this paper, we instead take the radical approach of learning to map questions to vectorial feature representations. By mapping answers into the same space one can query any knowledge base independent of its schema, without requiring any grammar or lexicon. Our method is trained with a new optimization procedure combining stochastic gradient descent followed by a fine-tuning step using the weak supervision provided by blending automatically and collaboratively generated resources. We empirically demonstrate that our model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.
40. Temporal Analysis of Language through Neural Language Models
328 citations
We provide a method for automatically detecting change in language across time through a chronologically trained neural language model. We train the model on the Google Books Ngram corpus to obtain word vector representations specific to each year, and identify words that have changed significantly from 1900 to 2009. The model identifies words such as "cell" and "gay" as having changed during that time period. The model simultaneously identifies the specific years during which such words underwent change.
41. Human language reveals a universal positivity bias
328 citations
Using human evaluation of 100,000 words spread across 24 corpora in 10 languages diverse in origin and culture, we present evidence of a deep imprint of human sociality in language, observing that (1) the words of natural human language possess a universal positivity bias; (2) the estimated emotional content of words is consistent between languages under translation; and (3) this positivity bias is strongly independent of frequency of word usage. Alongside these general regularities, we describe inter-language variations in the emotional spectrum of languages which allow us to rank corpora. We also show how our word evaluations can be used to construct physical-like instruments for both real-time and offline measurement of the emotional content of large-scale texts.
42. Multilingual Models for Compositional Distributed Semantics
312 citations
We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of semantically equivalent sentences, while maintaining sufficient distance between those of dissimilar sentences. The models do not rely on word alignments or any syntactic information and are successfully applied to a number of diverse languages. We extend our approach to learn semantic representations at the document level, too. We evaluate these models on two cross-lingual document classification tasks, outperforming the prior state of the art. Through qualitative analysis and the study of pivoting effects we demonstrate that our representations are semantically plausible and can capture semantic relationships across languages without parallel data.
43. Lexicon Infused Phrase Embeddings for Named Entity Resolution
308 citations
Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as a byproduct generate highly informative vector representations for words, known as word embeddings. In this paper we present two contributions: a new form of learning word embeddings that can leverage information from relevant lexicons to improve the representations, and the first system to use neural word embeddings to achieve state-of-the-art results on named-entity recognition in both CoNLL and Ontonotes NER. Our system achieves an F1 score of 90.90 on the test set for CoNLL 2003---significantly better than any previous system trained on public data, and matching a system employing massive private industrial query-log data.
44. Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition
293 citations
Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed and empirically evaluated on a large vocabulary conversational telephone speech recognition task. Meanwhile, regarding to multi-GPU devices, the training process for LSTM networks is introduced and discussed. Experimental results demonstrate that the deep LSTM networks benefit from the depth and yield the state-of-the-art performance on this task.
45. An Information Retrieval Approach to Short Text Conversation
248 citations
Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue. We propose formalizing short text conversation as a search problem at the first step, and employing state-of-the-art information retrieval (IR) techniques to carry out the task. We investigate the significance as well as the limitation of the IR approach. Our experiments demonstrate that the retrieval-based model can make the system behave rather "intelligently", when combined with a huge repository of conversation data from social media.
46. Compositional Morphology for Word Representations and Language Modelling
235 citations
This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. When used for translation into morphologically rich languages with large vocabularies, our models obtain improvements of up to 1.2 BLEU points relative to a baseline system using back-off n-gram models.
47. LABR: A Large Scale Arabic Sentiment Analysis Benchmark
234 citations
We introduce LABR, the largest sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars. We investigate the properties of the dataset, and present its statistics. We explore using the dataset for two tasks: (1) sentiment polarity classification; and (2) ratings classification. Moreover, we provide standard splits of the dataset into training, validation and testing, for both polarity and ratings classification, in both balanced and unbalanced settings. We extend our previous work by performing a comprehensive analysis on the dataset. In particular, we perform an extended survey of the different classifiers typically used for the sentiment polarity classification problem. We also construct a sentiment lexicon from the dataset that contains both single and compound sentiment words and we explore its effectiveness. We make the dataset and experimental details publicly available.
48. Coherent Multi-Sentence Video Description with Variable Level of Detail
208 citations
Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from the SR. To produce consistent multi-sentence descriptions, we model across-sentence consistency at the level of the SR by enforcing a consistent topic. We also contribute both to the visual recognition of objects proposing a hand-centric approach as well as to the robust generation of sentences using a word lattice. Human judges rate our multi-sentence descriptions as more readable, correct, and relevant than related work. To understand the difference between more detailed and shorter descriptions, we collect and analyze a video description corpus of three levels of detail.
49. Home Location Identification of Twitter Users
207 citations
We present a new algorithm for inferring the home location of Twitter users at different granularities, including city, state, time zone or geographic region, using the content of users tweets and their tweeting behavior. Unlike existing approaches, our algorithm uses an ensemble of statistical and heuristic classifiers to predict locations and makes use of a geographic gazetteer dictionary to identify place-name entities. We find that a hierarchical classification approach, where time zone, state or geographic region is predicted first and city is predicted next, can improve prediction accuracy. We have also analyzed movement variations of Twitter users, built a classifier to predict whether a user was travelling in a certain period of time and use that to further improve the location detection accuracy. Experimental evidence suggests that our algorithm works well in practice and outperforms the best existing algorithms for predicting the home location of Twitter users.
50. Exploiting Social Network Structure for Person-to-Person Sentiment Analysis
207 citations
Person-to-person evaluations are prevalent in all kinds of discourse and important for establishing reputations, building social bonds, and shaping public opinion. Such evaluations can be analyzed separately using signed social networks and textual sentiment analysis, but this misses the rich interactions between language and social context. To capture such interactions, we develop a model that predicts individual A's opinion of individual B by synthesizing information from the signed social network in which A and B are embedded with sentiment analysis of the evaluative texts relating A to B. We prove that this problem is NP-hard but can be relaxed to an efficiently solvable hinge-loss Markov random field, and we show that this implementation outperforms text-only and network-only versions in two very different datasets involving community-level decision-making: the Wikipedia Requests for Adminship corpus and the Convote U.S. Congressional speech corpus.
51. Scalable Topical Phrase Mining from Text Corpora
203 citations
While most topic modeling algorithms model text corpora with unigrams, human interpretation often relies on inherent grouping of terms into phrases. As such, we consider the problem of discovering topical phrases of mixed lengths. Existing work either performs post processing to the inference results of unigram-based topic models, or utilizes complex n-gram-discovery topic models. These methods generally produce low-quality topical phrases or suffer from poor scalability on even moderately-sized datasets. We propose a different approach that is both computationally efficient and effective. Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition. Our approach discovers high quality topical phrases with negligible extra cost to the bag-of-words topic model in a variety of datasets including research publication titles, abstracts, reviews, and news articles.
52. Cross-lingual Annotation Projection for Semantic Roles
199 citations
This article considers the task of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We propose a general framework that is based on annotation projection, phrased as a graph optimization problem. It is relatively inexpensive and has the potential to reduce the human effort involved in creating role-semantic resources. Within this framework, we present projection models that exploit lexical and syntactic information. We provide an experimental evaluation on an English-German parallel corpus which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data.
53. The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
190 citations
Consider a person trying to spread an important message on a social network. He/she can spend hours trying to craft the message. Does it actually matter? While there has been extensive prior work looking into predicting popularity of social-media content, the effect of wording per se has rarely been studied since it is often confounded with the popularity of the author and the topic. To control for these confounding factors, we take advantage of the surprising fact that there are many pairs of tweets containing the same url and written by the same user but employing different wording. Given such pairs, we ask: which version attracts more retweets? This turns out to be a more difficult task than predicting popular topics. Still, humans can answer this question better than chance (but far from perfectly), and the computational methods we develop can do better than both an average human and a strong competing method trained on non-controlled data.
54. How Many Topics? Stability Analysis for Topic Models
186 citations
Topic modeling refers to the task of discovering the underlying thematic structure in a text corpus, where the output is commonly presented as a report of the top terms appearing in each topic. Despite the diversity of topic modeling algorithms that have been proposed, a common challenge in successfully applying these techniques is the selection of an appropriate number of topics for a given corpus. Choosing too few topics will produce results that are overly broad, while choosing too many will result in the "over-clustering" of a corpus into many small, highly-similar topics. In this paper, we propose a term-centric stability analysis strategy to address this issue, the idea being that a model with an appropriate number of topics will be more robust to perturbations in the data. Using a topic modeling approach based on matrix factorization, evaluations performed on a range of corpora show that this strategy can successfully guide the model selection process.
55. Learning a Recurrent Visual Representation for Image Caption Generation
186 citations
In this paper we explore the bi-directional mapping between images and their sentence-based descriptions. We propose learning this mapping using a recurrent neural network. Unlike previous approaches that map both sentences and images to a common embedding, we enable the generation of novel sentences given an image. Using the same model, we can also reconstruct the visual features associated with an image given its visual description. We use a novel recurrent visual memory that automatically learns to remember long-term visual concepts to aid in both sentence generation and visual feature reconstruction. We evaluate our approach on several tasks. These include sentence generation, sentence retrieval and image retrieval. State-of-the-art results are shown for the task of generating novel image descriptions. When compared to human generated captions, our automatically generated captions are preferred by humans over $19.8\%$ of the time. Results are better than or comparable to state-of-the-art results on the image and sentence retrieval tasks for methods using similar visual features.
56. Learning to Win by Reading Manuals in a Monte-Carlo Framework
185 citations
Domain knowledge is crucial for effective performance in autonomous control systems. Typically, human effort is required to encode this knowledge into a control algorithm. In this paper, we present an approach to language grounding which automatically interprets text in the context of a complex control application, such as a game, and uses domain knowledge extracted from the text to improve control performance. Both text analysis and control strategies are learned jointly using only a feedback signal inherent to the application. To effectively leverage textual information, our method automatically extracts the text segment most relevant to the current game state, and labels it with a task-centric predicate structure. This labeled text is then used to bias an action selection policy for the game, guiding it towards promising regions of the action space. We encode our model for text analysis and game playing in a multi-layer neural network, representing linguistic decisions via latent variables in the hidden layers, and game action quality via the output layer. Operating within the Monte-Carlo Search framework, we estimate model parameters using feedback from simulated games. We apply our approach to the complex strategy game Civilization II using the official game manual as the text guide. Our results show that a linguistically-informed game-playing agent significantly outperforms its language-unaware counterpart, yielding a 34% absolute improvement and winning over 65% of games when playing against the built-in AI of Civilization.
57. DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News
180 citations
While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage. In this paper, we present a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood. Our approach exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from rappler.com. By providing new state-of-the-art performances in unsupervised settings for regression and classification tasks, even using a na\"{\i}ve approach, our experiments show the beneficial impact of harvesting social media data for affective lexicon building.
58. POLYGLOT-NER: Massive Multilingual Named Entity Recognition
171 citations
The increasing diversity of languages used on the web introduces a new level of complexity to Information Retrieval (IR) systems. We can no longer assume that textual content is written in one language or even the same language family. In this paper, we demonstrate how to build massive multilingual annotators with minimal human expertise and intervention. We describe a system that builds Named Entity Recognition (NER) annotators for 40 major languages using Wikipedia and Freebase. Our approach does not require NER human annotated datasets or language specific resources like treebanks, parallel corpora, and orthographic rules. The novelty of approach lies therein - using only language agnostic techniques, while achieving competitive performance. Our method learns distributed word representations (word embeddings) which encode semantic and syntactic features of words in each language. Then, we automatically generate datasets from Wikipedia link structure and Freebase attributes. Finally, we apply two preprocessing stages (oversampling and exact surface form matching) which do not require any linguistic expertise. Our evaluation is two fold: First, we demonstrate the system performance on human annotated datasets. Second, for languages where no gold-standard benchmarks are available, we propose a new method, distant evaluation, based on statistical machine translation.
59. Word Network Topic Model: A Simple but General Solution for Short and Imbalanced Texts
170 citations
The short text has been the prevalent format for information of Internet in recent decades, especially with the development of online social media, whose millions of users generate a vast number of short messages everyday. Although sophisticated signals delivered by the short text make it a promising source for topic modeling, its extreme sparsity and imbalance brings unprecedented challenges to conventional topic models like LDA and its variants. Aiming at presenting a simple but general solution for topic modeling in short texts, we present a word co-occurrence network based model named WNTM to tackle the sparsity and imbalance simultaneously. Different from previous approaches, WNTM models the distribution over topics for each word instead of learning topics for each document, which successfully enhance the semantic density of data space without importing too much time or space complexity. Meanwhile, the rich contextual information preserved in the word-word space also guarantees its sensitivity in identifying rare topics with convincing quality. Furthermore, employing the same Gibbs sampling with LDA makes WNTM easily to be extended to various application scenarios. Extensive validations on both short and normal texts testify the outperformance of WNTM as compared to baseline methods. And finally we also demonstrate its potential in precisely discovering newly emerging topics or unexpected events in Weibo at pretty early stages.
60. Text Relatedness Based on a Word Thesaurus
169 citations
The computation of relatedness between two fragments of text in an automated manner requires taking into account a wide range of factors pertaining to the meaning the two fragments convey, and the pairwise relations between their words. Without doubt, a measure of relatedness between text segments must take into account both the lexical and the semantic relatedness between words. Such a measure that captures well both aspects of text relatedness may help in many tasks, such as text retrieval, classification and clustering. In this paper we present a new approach for measuring the semantic relatedness between words based on their implicit semantic links. The approach exploits only a word thesaurus in order to devise implicit semantic links between words. Based on this approach, we introduce Omiotis, a new measure of semantic relatedness between texts which capitalizes on the word-to-word semantic relatedness measure (SR) and extends it to measure the relatedness between texts. We gradually validate our method: we first evaluate the performance of the semantic relatedness measure between individual words, covering word-to-word similarity and relatedness, synonym identification and word analogy; then, we proceed with evaluating the performance of our method in measuring text-to-text semantic relatedness in two tasks, namely sentence-to-sentence similarity and paraphrase recognition. Experimental evaluation shows that the proposed method outperforms every lexicon-based method of semantic relatedness in the selected tasks and the used data sets, and competes well against corpus-based and hybrid approaches.
61. Sentence Compression as Tree Transduction
165 citations
This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framework. Experimental results on sentence compression bring significant improvements over a state-of-the-art model.
62. First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs
160 citations
We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accuracy. Second, we propose and evaluate a modified prefix-search decoding algorithm. This approach to decoding enables first-pass speech recognition with a language model, completely unaided by the cumbersome infrastructure of HMM-based systems. Experiments on the Wall Street Journal corpus demonstrate fairly competitive word error rates, and the importance of bi-directional network recurrence.
63. Real-Time Classification of Twitter Trends
150 citations
Social media users give rise to social trends as they share about common interests, which can be triggered by different reasons. In this work, we explore the types of triggers that spark trends on Twitter, introducing a typology with following four types: 'news', 'ongoing events', 'memes', and 'commemoratives'. While previous research has analyzed trending topics in a long term, we look at the earliest tweets that produce a trend, with the aim of categorizing trends early on. This would allow to provide a filtered subset of trends to end users. We analyze and experiment with a set of straightforward language-independent features based on the social spread of trends to categorize them into the introduced typology. Our method provides an efficient way to accurately categorize trending topics without need of external data, enabling news organizations to discover breaking news in real-time, or to quickly identify viral memes that might enrich marketing decisions, among others. The analysis of social features also reveals patterns associated with each type of trend, such as tweets about ongoing events being shorter as many were likely sent from mobile devices, or memes having more retweets originating from a few trend-setters.
64. Video In Sentences Out
150 citations
We present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it. Action class is rendered as a verb, participant objects as noun phrases, properties of those objects as adjectival modifiers in those noun phrases, spatial relations between those participants as prepositional phrases, and characteristics of the event as prepositional-phrase adjuncts and adverbial modifiers. Extracting the information needed to render these linguistic entities requires an approach to event recognition that recovers object tracks, the trackto-role assignments, and changing body posture.
65. One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations
145 citations
Discourse relations bind smaller linguistic units into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked arguments. A more subtle challenge is that it is not enough to represent the meaning of each argument of a discourse relation, because the relation may depend on links between lower-level components, such as entity mentions. Our solution computes distributional meaning representations by composition up the syntactic parse tree. A key difference from previous work on compositional distributional semantics is that we also compute representations for entity mentions, using a novel downward compositional pass. Discourse relations are predicted from the distributional representations of the arguments, and also of their coreferent entity mentions. The resulting system obtains substantial improvements over the previous state-of-the-art in predicting implicit discourse relations in the Penn Discourse Treebank.
66. Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews
137 citations
Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review). In the simplest settings, we discriminate only between positive and negative sentiment, turning the task into a standard binary classification problem. We compare several ma- chine learning approaches to this problem, and combine them to achieve the best possible results. We show how to use for this task the standard generative lan- guage models, which are slightly complementary to the state of the art techniques. We achieve strong results on a well-known dataset of IMDB movie reviews. Our results are easily reproducible, as we publish also the code needed to repeat the experiments. This should simplify further advance of the state of the art, as other researchers can combine their techniques with ours with little effort.
67. Context-Dependent Fine-Grained Entity Type Tagging
135 citations
Entity type tagging is the task of assigning category labels to each mention of an entity in a document. While standard systems focus on a small set of types, recent work (Ling and Weld, 2012) suggests that using a large fine-grained label set can lead to dramatic improvements in downstream tasks. In the absence of labeled training data, existing fine-grained tagging systems obtain examples automatically, using resolved entities and their types extracted from a knowledge base. However, since the appropriate type often depends on context (e.g. Washington could be tagged either as city or government), this procedure can result in spurious labels, leading to poorer generalization. We propose the task of context-dependent fine type tagging, where the set of acceptable labels for a mention is restricted to only those deducible from the local context (e.g. sentence or document). We introduce new resources for this task: 12,017 mentions annotated with their context-dependent fine types, and we provide baseline experimental results on this data.
68. Extraction of Salient Sentences from Labelled Documents
125 citations
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to identify and extract topic-relevant sentences. We also introduce a new scalable evaluation technique for automatic sentence extraction systems that avoids the need for time consuming human annotation of validation data.
69. Learning Document-Level Semantic Properties from Free-Text Annotations
123 citations
This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured, user-generated online content. One especially relevant domain is product reviews, which are often annotated by their authors with pros/cons keyphrases such as a real bargain or good value. These annotations are representative of the underlying semantic properties; however, unlike expert annotations, they are noisy: lay authors may use different labels to denote the same property, and some labels may be missing. To learn using such noisy annotations, we find a hidden paraphrase structure which clusters the keyphrases. The paraphrase structure is linked with a latent topic model of the review texts, enabling the system to predict the properties of unannotated documents and to effectively aggregate the semantic properties of multiple reviews. Our approach is implemented as a hierarchical Bayesian model with joint inference. We find that joint inference increases the robustness of the keyphrase clustering and encourages the latent topics to correlate with semantically meaningful properties. Multiple evaluations demonstrate that our model substantially outperforms alternative approaches for summarizing single and multiple documents into a set of semantically salient keyphrases.
70. Unsupervised Methods for Determining Object and Relation Synonyms on the Web
123 citations
The task of identifying synonymous relations and objects, or synonym resolution, is critical for high-quality information extraction. This paper investigates synonym resolution in the context of unsupervised information extraction, where neither hand-tagged training examples nor domain knowledge is available. The paper presents a scalable, fully-implemented system that runs in O(KN log N) time in the number of extractions, N, and the maximum number of synonyms per word, K. The system, called Resolver, introduces a probabilistic relational model for predicting whether two strings are co-referential based on the similarity of the assertions containing them. On a set of two million assertions extracted from the Web, Resolver resolves objects with 78% precision and 68% recall, and resolves relations with 90% precision and 35% recall. Several variations of resolvers probabilistic model are explored, and experiments demonstrate that under appropriate conditions these variations can improve F1 by 5%. An extension to the basic Resolver system allows it to handle polysemous names with 97% precision and 95% recall on a data set from the TREC corpus.
71. Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System
121 citations
We present NaturalOWL, a natural language generation system that produces texts describing individuals or classes of OWL ontologies. Unlike simpler OWL verbalizers, which typically express a single axiom at a time in controlled, often not entirely fluent natural language primarily for the benefit of domain experts, we aim to generate fluent and coherent multi-sentence texts for end-users. With a system like NaturalOWL, one can publish information in OWL on the Web, along with automatically produced corresponding texts in multiple languages, making the information accessible not only to computer programs and domain experts, but also end-users. We discuss the processing stages of NaturalOWL, the optional domain-dependent linguistic resources that the system can use at each stage, and why they are useful. We also present trials showing that when the domain-dependent llinguistic resources are available, NaturalOWL produces significantly better texts compared to a simpler verbalizer, and that the resources can be created with relatively light effort.
72. A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing
120 citations
Dual decomposition, and more generally Lagrangian relaxation, is a classical method for combinatorial optimization; it has recently been applied to several inference problems in natural language processing (NLP). This tutorial gives an overview of the technique. We describe example algorithms, describe formal guarantees for the method, and describe practical issues in implementing the algorithms. While our examples are predominantly drawn from the NLP literature, the material should be of general relevance to inference problems in machine learning. A central theme of this tutorial is that Lagrangian relaxation is naturally applied in conjunction with a broad class of combinatorial algorithms, allowing inference in models that go significantly beyond previous work on Lagrangian relaxation for inference in graphical models.
73. How to Ask for a Favor: A Case Study on the Success of Altruistic Requests
119 citations
Requests are at the core of many social media systems such as question & answer sites and online philanthropy communities. While the success of such requests is critical to the success of the community, the factors that lead community members to satisfy a request are largely unknown. Success of a request depends on factors like who is asking, how they are asking, when are they asking, and most critically what is being requested, ranging from small favors to substantial monetary donations. We present a case study of altruistic requests in an online community where all requests ask for the very same contribution and do not offer anything tangible in return, allowing us to disentangle what is requested from textual and social factors. Drawing from social psychology literature, we extract high-level social features from text that operationalize social relations between recipient and donor and demonstrate that these extracted relations are predictive of success. More specifically, we find that clearly communicating need through the narrative is essential and that that linguistic indications of gratitude, evidentiality, and generalized reciprocity, as well as high status of the asker further increase the likelihood of success. Building on this understanding, we develop a model that can predict the success of unseen requests, significantly improving over several baselines. We link these findings to research in psychology on helping behavior, providing a basis for further analysis of success in social media systems.
74. Evaluating Neural Word Representations in Tensor-Based Compositional Settings
114 citations
We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based compositional models, which we then test (together with simpler additive and multiplicative approaches) in tasks involving verb disambiguation and sentence similarity. To check their scalability, we additionally evaluate the spaces using simple compositional methods on larger-scale tasks with less constrained language: paraphrase detection and dialogue act tagging. In the more constrained tasks, co-occurrence vectors are competitive, although choice of compositional method is important; on the larger-scale tasks, they are outperformed by neural word embeddings, which show robust, stable performance across the tasks.
75. Radical-Enhanced Chinese Character Embedding
113 citations
We present a method to leverage radical for learning Chinese character embedding. Radical is a semantic and phonetic component of Chinese character. It plays an important role as characters with the same radical usually have similar semantic meaning and grammatical usage. However, existing Chinese processing algorithms typically regard word or character as the basic unit but ignore the crucial radical information. In this paper, we fill this gap by leveraging radical for learning continuous representation of Chinese character. We develop a dedicated neural architecture to effectively learn character embedding and apply it on Chinese character similarity judgement and Chinese word segmentation. Experiment results show that our radical-enhanced method outperforms existing embedding learning algorithms on both tasks.
76. Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language
113 citations
We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision consisting of a stream of descriptive textual comments and a sequence of events extracted from the simulation trace. The system simultaneously establishes correspondences between individual comments and the events that they describe while building a translation model that supports both parsing and generation. We also present a novel algorithm for learning which events are worth describing. Human evaluations of the generated commentaries indicate they are of reasonable quality and in some cases even on par with those produced by humans for our limited domain.
77. Information Evolution in Social Networks
112 citations
Social networks readily transmit information, albeit with less than perfect fidelity. We present a large-scale measurement of this imperfect information copying mechanism by examining the dissemination and evolution of thousands of memes, collectively replicated hundreds of millions of times in the online social network Facebook. The information undergoes an evolutionary process that exhibits several regularities. A meme's mutation rate characterizes the population distribution of its variants, in accordance with the Yule process. Variants further apart in the diffusion cascade have greater edit distance, as would be expected in an iterative, imperfect replication process. Some text sequences can confer a replicative advantage; these sequences are abundant and transfer "laterally" between different memes. Subpopulations of the social network can preferentially transmit a specific variant of a meme if the variant matches their beliefs or culture. Understanding the mechanism driving change in diffusing information has important implications for how we interpret and harness the information that reaches us through our social networks.
78. Building DNN Acoustic Models for Large Vocabulary Speech Recognition
109 citations
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training loss function. This paper offers an empirical investigation on which aspects of DNN acoustic model design are most important for speech recognition system performance. We report DNN classifier performance and final speech recognizer word error rates, and compare DNNs using several metrics to quantify factors influencing differences in task performance. Our first set of experiments use the standard Switchboard benchmark corpus, which contains approximately 300 hours of conversational telephone speech. We compare standard DNNs to convolutional networks, and present the first experiments using locally-connected, untied neural networks for acoustic modeling. We additionally build systems on a corpus of 2,100 hours of training data by combining the Switchboard and Fisher corpora. This larger corpus allows us to more thoroughly examine performance of large DNN models -- with up to ten times more parameters than those typically used in speech recognition systems. Our results suggest that a relatively simple DNN architecture and optimization technique produces strong results. These findings, along with previous work, help establish a set of best practices for building DNN hybrid speech recognition systems with maximum likelihood training. Our experiments in DNN optimization additionally serve as a case study for training DNNs with discriminative loss functions for speech tasks, as well as DNN classifiers more generally.
79. The Frobenius anatomy of word meanings I: subject and object relative pronouns
102 citations
This paper develops a compositional vector-based semantics of subject and object relative pronouns within a categorical framework. Frobenius algebras are used to formalise the operations required to model the semantics of relative pronouns, including passing information between the relative clause and the modified noun phrase, as well as copying, combining, and discarding parts of the relative clause. We develop two instantiations of the abstract semantics, one based on a truth-theoretic approach and one based on corpus statistics.
80. Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
101 citations
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while preserving distinctions of word and sentence order crucial for capturing nuanced semantics. Our model is based on an extended Dynamic Convolution Neural Network, which learns convolution filters at both the sentence and document level, hierarchically learning to capture and compose low level lexical features into high level semantic concepts. We demonstrate the effectiveness of this model on a range of document modelling tasks, achieving strong results with no feature engineering and with a more compact model. Inspired by recent advances in visualising deep convolution networks for computer vision, we present a novel visualisation technique for our document networks which not only provides insight into their learning process, but also can be interpreted to produce a compelling automatic summarisation system for texts.
81. Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data
100 citations
We present in this paper an application which automatically generates textual short-term weather forecasts for every municipality in Galicia (NW Spain), using the real data provided by the Galician Meteorology Agency (MeteoGalicia). This solution combines in an innovative way computing with perceptions techniques and strategies for linguistic description of data together with a natural language generation (NLG) system. The application, named GALiWeather, extracts relevant information from weather forecast input data and encodes it into intermediate descriptions using linguistic variables and temporal references. These descriptions are later translated into natural language texts by the natural language generation system. The obtained forecast results have been thoroughly validated by an expert meteorologist from MeteoGalicia using a quality assessment methodology which covers two key dimensions of a text: the accuracy of its content and the correctness of its form. Following this validation GALiWeather will be released as a real service offering custom forecasts for a wide public.
82. That's sick dude!: Automatic identification of word sense change across different timescales
98 citations
In this paper, we propose an unsupervised method to identify noun sense changes based on rigorous analysis of time-varying text data available in the form of millions of digitized books. We construct distributional thesauri based networks from data at different time points and cluster each of them separately to obtain word-centric sense clusters corresponding to the different time points. Subsequently, we compare these sense clusters of two different time points to find if (i) there is birth of a new sense or (ii) if an older sense has got split into more than one sense or (iii) if a newer sense has been formed from the joining of older senses or (iv) if a particular sense has died. We conduct a thorough evaluation of the proposed methodology both manually as well as through comparison with WordNet. Manual evaluation indicates that the algorithm could correctly identify 60.4% birth cases from a set of 48 randomly picked samples and 57% split/join cases from a set of 21 randomly picked samples. Remarkably, in 44% cases the birth of a novel sense is attested by WordNet, while in 46% cases and 43% cases split and join are respectively confirmed by WordNet. Our approach can be applied for lexicography, as well as for applications like word sense disambiguation or semantic search.
83. Generating Extractive Summaries of Scientific Paradigms
93 citations
Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.
84. Crowdsourcing Dialect Characterization through Twitter
92 citations
We perform a large-scale analysis of language diatopic variation using geotagged microblogging datasets. By collecting all Twitter messages written in Spanish over more than two years, we build a corpus from which a carefully selected list of concepts allows us to characterize Spanish varieties on a global scale. A cluster analysis proves the existence of well defined macroregions sharing common lexical properties. Remarkably enough, we find that Spanish language is split into two superdialects, namely, an urban speech used across major American and Spanish citites and a diverse form that encompasses rural areas and small towns. The latter can be further clustered into smaller varieties with a stronger regional character.
85. A Method for Stopping Active Learning Based on Stabilizing Predictions and the Need for User-Adjustable Stopping
91 citations
A survey of existing methods for stopping active learning (AL) reveals the needs for methods that are: more widely applicable; more aggressive in saving annotations; and more stable across changing datasets. A new method for stopping AL based on stabilizing predictions is presented that addresses these needs. Furthermore, stopping methods are required to handle a broad range of different annotation/performance tradeoff valuations. Despite this, the existing body of work is dominated by conservative methods with little (if any) attention paid to providing users with control over the behavior of stopping methods. The proposed method is shown to fill a gap in the level of aggressiveness available for stopping AL and supports providing users with control over stopping behavior.
86. Supervised learning Methods for Bangla Web Document Categorization
87 citations
This paper explores the use of machine learning approaches, or more specifically, four supervised learning Methods, namely Decision Tree(C 4.5), K-Nearest Neighbour (KNN), Na\"ive Bays (NB), and Support Vector Machine (SVM) for categorization of Bangla web documents. This is a task of automatically sorting a set of documents into categories from a predefined set. Whereas a wide range of methods have been applied to English text categorization, relatively few studies have been conducted on Bangla language text categorization. Hence, we attempt to analyze the efficiency of those four methods for categorization of Bangla documents. In order to validate, Bangla corpus from various websites has been developed and used as examples for the experiment. For Bangla, empirical results support that all four methods produce satisfactory performance with SVM attaining good result in terms of high dimensional and relatively noisy document feature vectors.
87. Analyzing the Language of Food on Social Media
86 citations
We investigate the predictive power behind the language of food on social media. We collect a corpus of over three million food-related posts from Twitter and demonstrate that many latent population characteristics can be directly predicted from this data: overweight rate, diabetes rate, political leaning, and home geographical location of authors. For all tasks, our language-based models significantly outperform the majority-class baselines. Performance is further improved with more complex natural language processing, such as topic modeling. We analyze which textual features have most predictive power for these datasets, providing insight into the connections between the language of food, geographic locale, and community characteristics. Lastly, we design and implement an online system for real-time query and visualization of the dataset. Visualization tools, such as geo-referenced heatmaps, semantics-preserving wordclouds and temporal histograms, allow us to discover more complex, global patterns mirrored in the language of food.
88. Kaldi+PDNN: Building DNN-based ASR Systems with Kaldi and PDNN
82 citations
The Kaldi toolkit is becoming popular for constructing automated speech recognition (ASR) systems. Meanwhile, in recent years, deep neural networks (DNNs) have shown state-of-the-art performance on various ASR tasks. This document describes our open-source recipes to implement fully-fledged DNN acoustic modeling using Kaldi and PDNN. PDNN is a lightweight deep learning toolkit developed under the Theano environment. Using these recipes, we can build up multiple systems including DNN hybrid systems, convolutional neural network (CNN) systems and bottleneck feature systems. These recipes are directly based on the Kaldi Switchboard 110-hour setup. However, adapting them to new datasets is easy to achieve.
89. Controversy and Sentiment in Online News
82 citations
How do news sources tackle controversial issues? In this work, we take a data-driven approach to understand how controversy interplays with emotional expression and biased language in the news. We begin by introducing a new dataset of controversial and non-controversial terms collected using crowdsourcing. Then, focusing on 15 major U.S. news outlets, we compare millions of articles discussing controversial and non-controversial issues over a span of 7 months. We find that in general, when it comes to controversial issues, the use of negative affect and biased language is prevalent, while the use of strong emotion is tempered. We also observe many differences across news sources. Using these findings, we show that we can indicate to what extent an issue is controversial, by comparing it with other issues in terms of how they are portrayed across different media.
90. Learning Bilingual Word Representations by Marginalizing Alignments
80 citations
We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard alignments. The advantage of this approach is demonstrated in a cross-lingual classification task, where we outperform the prior published state of the art.
91. Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
78 citations
The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems. In this paper, we propose a way to address this issue by automatically segmenting an input sentence into phrases that can be easily translated by the neural network translation model. Once each segment has been independently translated by the neural machine translation model, the translated clauses are concatenated to form a final translation. Empirical results show a significant improvement in translation quality for long sentences.
92. Conditional Random Field Autoencoders for Unsupervised Structured Prediction
78 citations
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features. Each input's latent representation is predicted conditional on the observable data using a feature-rich conditional random field. Then a reconstruction of the input is (re)generated, conditional on the latent structure, using models for which maximum likelihood estimation has a closed-form. Our autoencoder formulation enables efficient learning without making unrealistic independence assumptions or restricting the kinds of features that can be used. We illustrate insightful connections to traditional autoencoders, posterior regularization and multi-view learning. We show competitive results with instantiations of the model for two canonical NLP tasks: part-of-speech induction and bitext word alignment, and show that training our model can be substantially more efficient than comparable feature-rich baselines.
93. Using Linguistic Features to Estimate Suicide Probability of Chinese Microblog Users
77 citations
If people with high risk of suicide can be identified through social media like microblog, it is possible to implement an active intervention system to save their lives. Based on this motivation, the current study administered the Suicide Probability Scale(SPS) to 1041 weibo users at Sina Weibo, which is a leading microblog service provider in China. Two NLP (Natural Language Processing) methods, the Chinese edition of Linguistic Inquiry and Word Count (LIWC) lexicon and Latent Dirichlet Allocation (LDA), are used to extract linguistic features from the Sina Weibo data. We trained predicting models by machine learning algorithm based on these two types of features, to estimate suicide probability based on linguistic features. The experiment results indicate that LDA can find topics that relate to suicide probability, and improve the performance of prediction. Our study adds value in prediction of suicidal probability of social network users with their behaviors.
94. Natural Language Processing in Biomedicine: A Unified System Architecture Overview
74 citations
In modern electronic medical records (EMR) much of the clinically important data - signs and symptoms, symptom severity, disease status, etc. - are not provided in structured data fields, but rather are encoded in clinician generated narrative text. Natural language processing (NLP) provides a means of "unlocking" this important data source for applications in clinical decision support, quality assurance, and public health. This chapter provides an overview of representative NLP systems in biomedicine based on a unified architectural view. A general architecture in an NLP system consists of two main components: background knowledge that includes biomedical knowledge resources and a framework that integrates NLP tools to process text. Systems differ in both components, which we will review briefly. Additionally, challenges facing current research efforts in biomedical NLP include the paucity of large, publicly available annotated corpora, although initiatives that facilitate data sharing, system evaluation, and collaborative work between researchers in clinical NLP are starting to emerge.
95. Choice of Mel Filter Bank in Computing MFCC of a Resampled Speech
74 citations
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this paper, we study the effect of resampling a speech signal on these speech features. We first derive a relationship between the MFCC param- eters of the resampled speech and the MFCC parameters of the original speech. We propose six methods of calculating the MFCC parameters of downsampled speech by transforming the Mel filter bank used to com- pute MFCC of the original speech. We then experimentally compute the MFCC parameters of the down sampled speech using the proposed meth- ods and compute the Pearson coefficient between the MFCC parameters of the downsampled speech and that of the original speech to identify the most effective choice of Mel-filter band that enables the computed MFCC of the resampled speech to be as close as possible to the original speech sample MFCC.
96. Narrowing the Modeling Gap: A Cluster-Ranking Approach to Coreference Resolution
73 citations
Traditional learning-based coreference resolvers operate by training the mention-pair model for determining whether two mentions are coreferent or not. Though conceptually simple and easy to understand, the mention-pair model is linguistically rather unappealing and lags far behind the heuristic-based coreference models proposed in the pre-statistical NLP era in terms of sophistication. Two independent lines of recent research have attempted to improve the mention-pair model, one by acquiring the mention-ranking model to rank preceding mentions for a given anaphor, and the other by training the entity-mention model to determine whether a preceding cluster is coreferent with a given mention. We propose a cluster-ranking approach to coreference resolution, which combines the strengths of the mention-ranking model and the entity-mention model, and is therefore theoretically more appealing than both of these models. In addition, we seek to improve cluster rankers via two extensions: (1) lexicalization and (2) incorporating knowledge of anaphoricity by jointly modeling anaphoricity determination and coreference resolution. Experimental results on the ACE data sets demonstrate the superior performance of cluster rankers to competing approaches as well as the effectiveness of our two extensions.
97. Tripartite Graph Clustering for Dynamic Sentiment Analysis on Social Media
72 citations
The growing popularity of social media (e.g, Twitter) allows users to easily share information with each other and influence others by expressing their own sentiments on various subjects. In this work, we propose an unsupervised \emph{tri-clustering} framework, which analyzes both user-level and tweet-level sentiments through co-clustering of a tripartite graph. A compelling feature of the proposed framework is that the quality of sentiment clustering of tweets, users, and features can be mutually improved by joint clustering. We further investigate the evolution of user-level sentiments and latent feature vectors in an online framework and devise an efficient online algorithm to sequentially update the clustering of tweets, users and features with newly arrived data. The online framework not only provides better quality of both dynamic user-level and tweet-level sentiment analysis, but also improves the computational and storage efficiency. We verified the effectiveness and efficiency of the proposed approaches on the November 2012 California ballot Twitter data.
98. Bucking the Trend: Large-Scale Cost-Focused Active Learning for Statistical Machine Translation
72 citations
We explore how to improve machine translation systems by adding more translation data in situations where we already have substantial resources. The main challenge is how to buck the trend of diminishing returns that is commonly encountered. We present an active learning-style data solicitation algorithm to meet this challenge. We test it, gathering annotations via Amazon Mechanical Turk, and find that we get an order of magnitude increase in performance rates of improvement.
99. Zipf's law for word frequencies: word forms versus lemmas in long texts
71 citations
Zipf's law is a fundamental paradigm in the statistics of written and spoken natural language as well as in other communication systems. We raise the question of the elementary units for which Zipf's law should hold in the most natural way, studying its validity for plain word forms and for the corresponding lemma forms. In order to have as homogeneous sources as possible, we analyze some of the longest literary texts ever written, comprising four different languages, with different levels of morphological complexity. In all cases Zipf's law is fulfilled, in the sense that a power-law distribution of word or lemma frequencies is valid for several orders of magnitude. We investigate the extent to which the word-lemma transformation preserves two parameters of Zipf's law: the exponent and the low-frequency cut-off. We are not able to demonstrate a strict invariance of the tail, as for a few texts both exponents deviate significantly, but we conclude that the exponents are very similar, despite the remarkable transformation that going from words to lemmas represents, considerably affecting all ranges of frequencies. In contrast, the low-frequency cut-offs are less stable.
100. Opinion mining of movie reviews at document level
71 citations
The whole world is changed rapidly and using the current technologies Internet becomes an essential need for everyone. Web is used in every field. Most of the people use web for a common purpose like online shopping, chatting etc. During an online shopping large number of reviews/opinions are given by the users that reflect whether the product is good or bad. These reviews need to be explored, analyse and organized for better decision making. Opinion Mining is a natural language processing task that deals with finding orientation of opinion in a piece of text with respect to a topic. In this paper a document based opinion mining system is proposed that classify the documents as positive, negative and neutral. Negation is also handled in the proposed system. Experimental results using reviews of movies show the effectiveness of the system.