COLING 2018 论文列表

Word sense disambiguation (WSD) is the task to determine the word sense according to its context. Many existing WSD studies have been using an external knowledge-based unsupervised approach because it has fewer word set constraints than supervised approaches requiring training data. In this paper, we propose a new WSD method to generate the context of an ambiguous word by using similarities between an ambiguous word and words in the input document. In addition, to leverage our WSD method, we further propose a new word similarity calculation method based on the semantic network structure of BabelNet. We evaluate the proposed methods on the SemEval-13 and SemEval-15 for English WSD dataset. Experimental results demonstrate that the proposed WSD method significantly improves the baseline WSD method. Furthermore, our WSD system outperforms the state-of-the-art WSD systems in the Semeval-13 dataset. Finally, it has higher performance than the state-of-the-art unsupervised knowledge-based WSD system in the average performance of both datasets.

Attempts to find a single technique for general-purpose intrinsic evaluation of word embeddings have so far not been successful. We present a new approach based on scaled-up qualitative analysis of word vector neighborhoods that quantifies interpretable characteristics of a given model (e.g. its preference for synonyms or shared morphological forms as nearest neighbors). We analyze 21 such factors and show how they correlate with performance on 14 extrinsic and intrinsic task datasets (and also explain the lack of correlation between some of them). Our approach enables multi-faceted evaluation, parameter search, and generally – a more principled, hypothesis-driven approach to development of distributional semantic representations.

Formulaic expressions (FEs) used in scholarly papers, such as ‘there has been little discussion about’, are helpful for non-native English speakers. However, it is time-consuming for users to manually search for an appropriate expression every time they want to consult FE dictionaries. For this reason, we tackle the task of semantic searches of FE dictionaries. At the start of our research, we identified two salient difficulties in this task. First, the paucity of example sentences in existing FE dictionaries results in a shortage of context information, which is necessary for acquiring semantic representation of FEs. Second, while a semantic category label is assigned to each FE in many FE dictionaries, it is difficult to predict the labels from user input, forcing users to manually designate the semantic category when searching. To address these difficulties, we propose a new framework for semantic searches of FEs and propose a new method to leverage both existing dictionaries and domain sentence corpora. Further, we expand an existing FE dictionary to consider building a more comprehensive and domain-specific FE dictionary and to verify the effectiveness of our method.

We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks. Our results confirm that weighted vector averaging can outperform context-sensitive models in most benchmarks, but structural features encoded in RNN models can also be useful in certain classification tasks. We analyzed some of the evaluation datasets to identify the aspects of meaning they measure and the characteristics of the various models that explain their performance variance.

We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector space. We propose a simple pipeline for learning such relation vectors, which is based on word vector averaging in combination with an ad hoc autoencoder. We show that by explicitly encoding relational information in a dedicated vector space we can capture aspects of word meaning that are complementary to what is captured by word embeddings. For example, by examining clusters of relation vectors, we observe that relational similarities can be identified at a more abstract level than with traditional word vector differences. Finally, we test the effectiveness of semantic vector networks in two tasks: measuring word similarity and neural text categorization. SeVeN is available at bitbucket.org/luisespinosa/seven.

Commonsense, real-world knowledge about the events that entities or “things in the world” are typically involved in, as well as part-whole relationships, is valuable for allowing computational systems to draw everyday inferences about the world. Here, we focus on automatically extracting information about (1) the events that typically bring about certain entities (origins), (2) the events that are the typical functions of entities, and (3) part-whole relationships in entities. These correspond to the agentive, telic and constitutive qualia central to the Generative Lexicon. We describe our motivations and methods for extracting these qualia relations from the Suggested Upper Merged Ontology (SUMO) and show that human annotators overwhelmingly find the information extracted to be reasonable. Because ontologies provide a way of structuring this information and making it accessible to agents and computational systems generally, efforts are underway to incorporate the extracted information to an ontology hub of Natural Language Processing semantic role labeling resources, the Rich Event Ontology.

Text generation may require the pluralization of nouns, such as in context-sensitive user interfaces and in natural language generation more broadly. While this has been solved for the widely-used languages, this is still a challenge for the languages in the Bantu language family. Pluralization results obtained for isiZulu and Runyankore showed there were similarities in approach, including the need to combine syntax with semantics, despite belonging to different language zones. This suggests that bootstrapping and generalizability might be feasible. We investigated this systematically for seven languages across three different Guthrie language zones. The first outcome is that Meinhof’s 1948 specification of the noun classes are indeed inadequate for computational purposes for all examined languages, due to non-determinism in prefixes, and we thus redefined the characteristic noun class tables of 29 noun classes into 53. The second main result is that the generic pluralizer achieved over 93% accuracy in coverage testing and over 94% on a random sample. This is comparable to the language-specific isiZulu and Runyankore pluralizers.

In this article, we discuss which text, speech, and image technologies have been developed, and would be feasible to develop, for the approximately 60 Indigenous languages spoken in Canada. In particular, we concentrate on technologies that may be feasible to develop for most or all of these languages, not just those that may be feasible for the few most-resourced of these. We assess past achievements and consider future horizons for Indigenous language transliteration, text prediction, spell-checking, approximate search, machine translation, speech recognition, speaker diarization, speech synthesis, optical character recognition, and computer-aided language learning.

Scientific papers from all disciplines contain many abbreviations and acronyms. In many cases these acronyms are ambiguous. We present a method to choose the contextual correct definition of an acronym that does not require training for each acronym and thus can be applied to a large number of different acronyms with only few instances. We constructed a set of 19,954 examples of 4,365 ambiguous acronyms from image captions in scientific papers along with their contextually correct definition from different domains. We learn word embeddings for all words in the corpus and compare the averaged context vector of the words in the expansion of an acronym with the weighted average vector of the words in the context of the acronym. We show that this method clearly outperforms (classical) cosine similarity. Furthermore, we show that word embeddings learned from a 1 billion word corpus of scientific texts outperform word embeddings learned on much large general corpora.

Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first demystify the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. Based on this analysis, we then relax the assumption of training data required by most existing models, creating a model that only requires a dictionary for training. Experiments show that our new method effectively learns coherent multilingual topics from partially and fully incomparable corpora with limited amounts of dictionary resources.

Multiword expressions, especially verbal ones (VMWEs), show idiosyncratic variability, which is challenging for NLP applications, hence the need for VMWE identification. We focus on the task of variant identification, i.e. identifying variants of previously seen VMWEs, whatever their surface form. We model the problem as a classification task. Syntactic subtrees with previously seen combinations of lemmas are first extracted, and then classified on the basis of features relevant to morpho-syntactic variation of VMWEs. Feature values are both absolute, i.e. hold for a particular VMWE candidate, and relative, i.e. based on comparing a candidate with previously seen VMWEs. This approach outperforms a baseline by 4 percent points of F-measure on a French corpus.

In this article, we present ReSyf, a lexical resource of monolingual synonyms ranked according to their difficulty to be read and understood by native learners of French. The synonyms come from an existing lexical network and they have been semantically disambiguated and refined. A ranking algorithm, based on a wide range of linguistic features and validated through an evaluation campaign with human annotators, automatically sorts the synonyms corresponding to a given word sense by reading difficulty. ReSyf is freely available and will be integrated into a web platform for reading assistance. It can also be applied to perform lexical simplification of French texts.

State-of-the-art Natural Language Processing algorithms rely heavily on efficient word segmentation. Urdu is amongst languages for which word segmentation is a complex task as it exhibits space omission as well as space insertion issues. This is partly due to the Arabic script which although cursive in nature, consists of characters that have inherent joining and non-joining attributes regardless of word boundary. This paper presents a word segmentation system for Urdu which uses a Conditional Random Field sequence modeler with orthographic, linguistic and morphological features. Our proposed model automatically learns to predict white space as word boundary as well as Zero Width Non-Joiner (ZWNJ) as sub-word boundary. Using a manually annotated corpus, our model achieves F1 score of 0.97 for word boundary identification and 0.85 for sub-word boundary identification tasks. We have made our code and corpus publicly available to make our results reproducible.

Distributed representations of words play a major role in the field of natural language processing by encoding semantic and syntactic information of words. However, most existing works on learning word representations typically regard words as individual atomic units and thus are blind to subword information in words. This further gives rise to a difficulty in representing out-of-vocabulary (OOV) words. In this paper, we present a character-based word representation approach to deal with this limitation. The proposed model learns to generate word representations from characters. In our model, we employ a convolutional neural network and a highway network over characters to extract salient features effectively. Unlike previous models that learn word representations from a large corpus, we take a set of pre-trained word embeddings and generalize it to word entries, including OOV words. To demonstrate the efficacy of the proposed model, we perform both an intrinsic and an extrinsic task which are word similarity and language modeling, respectively. Experimental results show clearly that the proposed model significantly outperforms strong baseline models that regard words or their subwords as atomic units. For example, we achieve as much as 18.5% improvement on average in perplexity for morphologically rich languages compared to strong baselines in the language modeling task.

Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community. In this paper, we first build a novel QA matching corpus with informal text which is collected from a product reviewing website. Then, we propose a novel QA matching approach, namely One vs. Many Matching, which aims to address the novel scenario where one question sentence often has an answer with multiple sentences. Furthermore, we improve our matching approach by employing both word-level and sentence-level attentions for solving the noisy problem in the informal text. Empirical studies demonstrate the effectiveness of the proposed approach to question-answer matching.

Most work on part-of-speech (POS) tagging is focused on high resource languages, or examines low-resource and active learning settings through simulated studies. We evaluate POS tagging techniques on an actual endangered language, Griko. We present a resource that contains 114 narratives in Griko, along with sentence-level translations in Italian, and provides gold annotations for the test set. Based on a previously collected small corpus, we investigate several traditional methods, as well as methods that take advantage of monolingual data or project cross-lingual POS tags. We show that the combination of a semi-supervised method with cross-lingual transfer is more appropriate for this extremely challenging setting, with the best tagger achieving an accuracy of 72.9%. With an applied active learning scheme, which we use to collect sentence-level annotations over the test set, we achieve improvements of more than 21 percentage points.

In this paper we use methods for creating a large lexicon of verbal polarity shifters and apply them to German. Polarity shifters are content words that can move the polarity of a phrase towards its opposite, such as the verb “abandon” in “abandon all hope”. This is similar to how negation words like “not” can influence polarity. Both shifters and negation are required for high precision sentiment analysis. Lists of negation words are available for many languages, but the only language for which a sizable lexicon of verbal polarity shifters exists is English. This lexicon was created by bootstrapping a sample of annotated verbs with a supervised classifier that uses a set of data- and resource-driven features. We reproduce and adapt this approach to create a German lexicon of verbal polarity shifters. Thereby, we confirm that the approach works for multiple languages. We further improve classification by leveraging cross-lingual information from the English shifter lexicon. Using this improved approach, we bootstrap a large number of German verbal polarity shifters, reducing the annotation effort drastically. The resulting German lexicon of verbal polarity shifters is made publicly available.

Detecting changes within an unfolding event in real time from news articles or social media enables to react promptly to serious issues in public safety, public health or natural disasters. In this study, we use on-line Latent Dirichlet Allocation (LDA) to model shifts in topics, and apply on-line change point detection (CPD) algorithms to detect when significant changes happen. We describe an on-line Bayesian change point detection algorithm that we use to detect topic changes from on-line LDA output. Extensive experiments on social media data and news articles show the benefits of on-line LDA versus standard LDA, and of on-line change point detection compared to off-line algorithms. This yields F-scores up to 52% on the detection of significant real-life changes from these document streams.

Representing the semantic relations that exist between two given words (or entities) is an important first step in a wide-range of NLP applications such as analogical reasoning, knowledge base completion and relational information retrieval. A simple, yet surprisingly accurate method for representing a relation between two words is to compute the vector offset (PairDiff) between their corresponding word embeddings. Despite the empirical success, it remains unclear as to whether PairDiff is the best operator for obtaining a relational representation from word embeddings. We conduct a theoretical analysis of generalised bilinear operators that can be used to measure the l2 relational distance between two word-pairs. We show that, if the word embed- dings are standardised and uncorrelated, such an operator will be independent of bilinear terms, and can be simplified to a linear form, where PairDiff is a special case. For numerous word embedding types, we empirically verify the uncorrelation assumption, demonstrating the general applicability of our theoretical result. Moreover, we experimentally discover PairDiff from the bilinear relational compositional operator on several benchmark analogy datasets.