COLING 2018 论文列表

We extend the coverage of an existing grammar customization system to clausal modifiers, also referred to as adverbial clauses. We present an analysis, taking a typologically-driven approach to account for this phenomenon across the world’s languages, which we implement in the Grammar Matrix customization system (Bender et al., 2002, 2010). Testing our analysis on testsuites from five genetically and geographically diverse languages that were not considered in development, we achieve 88.4% coverage and 1.5% overgeneration.

Vulgarity is a common linguistic expression and is used to perform several linguistic functions. Understanding their usage can aid both linguistic and psychological phenomena as well as benefit downstream natural language processing applications such as sentiment analysis. This study performs a large-scale, data-driven empirical analysis of vulgar words using social media data. We analyze the socio-cultural and pragmatic aspects of vulgarity using tweets from users with known demographics. Further, we collect sentiment ratings for vulgar tweets to study the relationship between the use of vulgar words and perceived sentiment and show that explicitly modeling vulgar words can boost sentiment analysis performance.

Social media based micro-blogging sites like Twitter have become a common source of real-time information (impacting organizations and their strategies, and are used for expressing emotions and opinions. Automated analysis of such content therefore rises in importance. To this end, we explore the viability of using deep neural networks on the specific task of emotion intensity prediction in tweets. We propose a neural architecture combining convolutional and fully connected layers in a non-sequential manner - done for the first time in context of natural language based tasks. Combined with lexicon-based features along with transfer learning, our model achieves state-of-the-art performance, outperforming the previous system by 0.044 or 4.4% Pearson correlation on the WASSA’17 EmoInt shared task dataset. We investigate the performance of deep multi-task learning models trained for all emotions at once in a unified architecture and get encouraging results. Experiments performed on evaluating correlation between emotion pairs offer interesting insights into the relationship between them.

Detection and classification of emotion categories expressed by a sentence is a challenging task due to subjectivity of emotion. To date, most of the models are trained and evaluated on single genre and when used to predict emotion in different genre their performance drops by a large margin. To address the issue of robustness, we model the problem within a joint multi-task learning framework. We train this model with a multigenre emotion corpus to predict emotions across various genre. Each genre is represented as a separate task, we use soft parameter shared layers across the various tasks. our experimental results show that this model improves the results across the various genres, compared to a single genre training in the same neural net architecture.

Emotion Representation Mapping (ERM) has the goal to convert existing emotion ratings from one representation format into another one, e.g., mapping Valence-Arousal-Dominance annotations for words or sentences into Ekman’s Basic Emotions and vice versa. ERM can thus not only be considered as an alternative to Word Emotion Induction (WEI) techniques for automatic emotion lexicon construction but may also help mitigate problems that come from the proliferation of emotion representation formats in recent years. We propose a new neural network approach to ERM that not only outperforms the previous state-of-the-art. Equally important, we present a refined evaluation methodology and gather strong evidence that our model yields results which are (almost) as reliable as human annotations, even in cross-lingual settings. Based on these results we generate new emotion ratings for 13 typologically diverse languages and claim that they have near-gold quality, at least.

Folksonomy of movies covers a wide range of heterogeneous information about movies, like the genre, plot structure, visual experiences, soundtracks, metadata, and emotional experiences from watching a movie. Being able to automatically generate or predict tags for movies can help recommendation engines improve retrieval of similar movies, and help viewers know what to expect from a movie in advance. In this work, we explore the problem of creating tags for movies from plot synopses. We propose a novel neural network model that merges information from synopses and emotion flows throughout the plots to predict a set of tags for movies. We compare our system with multiple baselines and found that the addition of emotion flows boosts the performance of the network by learning ≈18% more tags than a traditional machine learning system.

Neural activation models have been proposed in the literature that use a set of example words for which fMRI measurements are available in order to find a mapping between word semantics and localized neural activations. Successful mappings let us expand to the full lexicon of concrete nouns using the assumption that similarity of meaning implies similar neural activation patterns. In this paper, we propose a computational model that estimates semantic similarity in the neural activation space and investigates the relative performance of this model for various natural language processing tasks. Despite the simplicity of the proposed model and the very small number of example words used to bootstrap it, the neural activation semantic model performs surprisingly well compared to state-of-the-art word embeddings. Specifically, the neural activation semantic model performs better than the state-of-the-art for the task of semantic similarity estimation between very similar or very dissimilar words, while performing well on other tasks such as entailment and word categorization. These are strong indications that neural activation semantic models can not only shed some light into human cognition but also contribute to computation models for certain tasks.

Extracting a bilingual terminology for multi-word terms from comparable corpora has not been widely researched. In this work we propose a unified framework for aligning bilingual terms independently of the term lengths. We also introduce some enhancements to the context-based and the neural network based approaches. Our experiments show the effectiveness of our enhancements of previous works and the system can be adapted in specialized domains.

Representing a word by its co-occurrences with other words in context is an effective way to capture the meaning of the word. However, the theory behind remains a challenge. In this work, taking the example of a word classification task, we give a theoretical analysis of the approaches that represent a word X by a function f(P(C|X)), where C is a context feature, P(C|X) is the conditional probability estimated from a text corpus, and the function f maps the co-occurrence measure to a prediction score. We investigate the impact of context feature C and the function f . We also explain the reasons why using the co-occurrences with multiple context features may be better than just using a single one. In addition, based on the analysis, we propose a hypothesis about the conditional probability on zero probability events.

Word composition is a promising technique for representation learning of large linguistic units (e.g., phrases, sentences and documents). However, most of the current composition models do not take the ambiguity of words and the context outside of a linguistic unit into consideration for learning representations, and consequently suffer from the inaccurate representation of semantics. To address this issue, we propose a model-free context-aware word composition model, which employs the latent semantic information as global context for learning representations. The proposed model attempts to resolve the word sense disambiguation and word composition in a unified framework. Extensive evaluation shows consistent improvements over various strong word representation/composition models at different granularities (including word, phrase and sentence), demonstrating the effectiveness of our proposed method.

Texts from the Internet serve as important data sources for financial market modeling. Early statistical approaches rely on manually defined features to capture lexical, sentiment and event information, which suffers from feature sparsity. Recent work has considered learning dense representations for news titles and abstracts. Compared to news titles, full documents can contain more potentially helpful information, but also noise compared to events and sentences, which has been less investigated in previous work. To fill this gap, we propose a novel target-specific abstract-guided news document representation model. The model uses a target-sensitive representation of the news abstract to weigh sentences in the news content, so as to select and combine the most informative sentences for market modeling. Results show that document representations can give better performance for estimating cumulative abnormal returns of companies when compared to titles and abstracts. Our model is especially effective when it used to combine information from multiple document sources compared to the sentence-level baselines.

Authorship attribution typically uses all information representing both content and style whereas attribution based only on stylistic aspects may be robust in cross-domain settings. This paper analyzes different linguistic aspects that may help represent style. Specifically, we study the role of syntax and lexical words (nouns, verbs, adjectives and adverbs) in representing style. We use a purely syntactic language model to study the significance of sentence structures in both single-domain and cross-domain attribution, i.e. cross-topic and cross-genre attribution. We show that syntax may be helpful for cross-genre attribution while cross-topic attribution and single-domain may benefit from additional lexical information. Further, pure syntactic models may not be effective by themselves and need to be used in combination with other robust models. To study the role of word choice, we perform attribution by masking all words or specific topic words corresponding to nouns, verbs, adjectives and adverbs. Using a single-domain dataset, IMDB1M reviews, we demonstrate the heavy influence of common nouns and proper nouns in attribution, thereby highlighting topic interference. Using cross-domain Guardian10 dataset, we show that some common nouns, verbs, adjectives and adverbs may help with stylometric attribution as demonstrated by masking topic words corresponding to these parts-of-speech. As expected, it was observed that proper nouns are heavily influenced by content and cross-domain attribution will benefit from completely masking them.

The rapid growth of documents across the web has necessitated finding means of discarding redundant documents and retaining novel ones. Capturing redundancy is challenging as it may involve investigating at a deep semantic level. Techniques for detecting such semantic redundancy at the document level are scarce. In this work we propose a deep Convolutional Neural Networks (CNN) based model to classify a document as novel or redundant with respect to a set of relevant documents already seen by the system. The system is simple and do not require any manual feature engineering. Our novel scheme encodes relevant and relative information from both source and target texts to generate an intermediate representation which we coin as the Relative Document Vector (RDV). The proposed method outperforms the existing state-of-the-art on a document-level novelty detection dataset by a margin of ∼5% in terms of accuracy. We further demonstrate the effectiveness of our approach on a standard paraphrase detection dataset where paraphrased passages closely resemble to semantically redundant documents.

The Business Process Management (BPM) field focuses in the coordination of labor so that organizational processes are smoothly executed in a way that products and services are properly delivered. At the same time, NLP has reached a maturity level that enables its widespread application in many contexts, thanks to publicly available frameworks. In this position paper, we show how NLP has potential in raising the benefits of BPM practices at different levels. Instead of being exhaustive, we show selected key challenges were a successful application of NLP techniques would facilitate the automation of particular tasks that nowadays require a significant effort to accomplish. Finally, we report on applications that consider both the process perspective and its enhancement through NLP.

Dealing with ‘open-vocabulary’ slots has been among the challenges in the natural language area. While recent studies on attention-based recurrent neural network (RNN) models have performed well in completing several language related tasks such as spoken language understanding and dialogue systems, there has been a lack of attempts to address filling slots that take on values from a virtually unlimited set. In this paper, we propose a new RNN model that can capture the vital concept: Understanding the role of a word may vary according to how long a reader focuses on a particular part of a sentence. The proposed model utilizes a long-term aware attention structure, positional encoding primarily considering the relative distance between words, and multi-task learning of a character-based language model and an intent detection model. We show that the model outperforms the existing RNN models with respect to discovering ‘open-vocabulary’ slots without any external information, such as a named entity database or knowledge base. In particular, we confirm that it performs better with a greater number of slots in a dataset, including unknown words, by evaluating the models on a dataset of several domains. In addition, the proposed model also demonstrates superior performance with regard to intent detection.

Most existing research on authorship attribution uses various lexical, syntactic and semantic features. In this paper we demonstrate an effective template-based approach for combining various syntactic features of a document for authorship analysis. The parse-tree based features that we propose are independent of the topic of a document and reflect the innate writing styles of authors. We show that the use of templates including sub-trees of parse trees in conjunction with other syntactic features result in improved author attribution rates. Another contribution is the demonstration that Dempster’s rule based combination of evidence from syntactic features performs better than other evidence-combination methods. We also demonstrate that our methodology works well for the case where actual author is not included in the candidate author set.

Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the semantic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models.

While much progress has been made in how to encode a text sequence into a sequence of vectors, less attention has been paid to how to aggregate these preceding vectors (outputs of RNN/CNN) into fixed-size encoding vector. Usually, a simple max or average pooling is used, which is a bottom-up and passive way of aggregation and lack of guidance by task information. In this paper, we propose an aggregation mechanism to obtain a fixed-size encoding with a dynamic routing policy. The dynamic routing policy is dynamically deciding that what and how much information need be transferred from each word to the final encoding of the text sequence. Following the work of Capsule Network, we design two dynamic routing policies to aggregate the outputs of RNN/CNN encoding layer into a final encoding vector. Compared to the other aggregation methods, dynamic routing can refine the messages according to the state of final encoding vector. Experimental results on five text classification tasks show that our method outperforms other aggregating models by a significant margin. Related source code is released on our github page. Related source code is released on our github page.

Several metrics have been proposed for evaluating grammatical error correction (GEC) systems based on grammaticality, fluency, and adequacy of the output sentences. Previous studies of the correlation of these metrics with human quality judgments were inconclusive, due to the lack of appropriate significance tests, discrepancies in the methods, and choice of datasets used. In this paper, we re-evaluate reference-based GEC metrics by measuring the system-level correlations with humans on a large dataset of human judgments of GEC outputs, and by properly conducting statistical significance tests. Our results show no significant advantage of GLEU over MaxMatch (M2), contradicting previous studies that claim GLEU to be superior. For a finer-grained analysis, we additionally evaluate these metrics for their agreement with human judgments at the sentence level. Our sentence-level analysis indicates that comparing GLEU and M2, one metric may be more useful than the other depending on the scenario. We further qualitatively analyze these metrics and our findings show that apart from being less interpretable and non-deterministic, GLEU also produces counter-intuitive scores in commonly occurring test examples.