David Vilares


2020

pdf bib
Bracketing Encodings for 2-Planar Dependency Parsing
Michalina Strzyz | David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 28th International Conference on Computational Linguistics

We present a bracketing-based encoding that can be used to represent any 2-planar dependency tree over a sentence of length n as a sequence of n labels, hence providing almost total coverage of crossing arcs in sequence labeling parsing. First, we show that existing bracketing encodings for parsing as labeling can only handle a very mild extension of projective trees. Second, we overcome this limitation by taking into account the well-known property of 2-planarity, which is present in the vast majority of dependency syntactic structures in treebanks, i.e., the arcs of a dependency tree can be split into two planes such that arcs in a given plane do not cross. We take advantage of this property to design a method that balances the brackets and that encodes the arcs belonging to each of those planes, allowing for almost unrestricted non-projectivity (∼99.9% coverage) in sequence labeling parsing. The experiments show that our linearizations improve over the accuracy of the original bracketing encoding in highly non-projective treebanks (on average by 0.4 LAS), while achieving a similar speed. Also, they are especially suitable when PoS tags are not used as input parameters to the models.

pdf bib
A Unifying Theory of Transition-based and Sequence Labeling Parsing
Carlos Gómez-Rodríguez | Michalina Strzyz | David Vilares
Proceedings of the 28th International Conference on Computational Linguistics

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms. Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.

pdf bib
Discontinuous Constituent Parsing as Sequence Labeling
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

This paper reduces discontinuous parsing to sequence labeling. It first shows that existing reductions for constituent parsing as labeling do not support discontinuities. Second, it fills this gap and proposes to encode tree discontinuities as nearly ordered permutations of the input sequence. Third, it studies whether such discontinuous representations are learnable. The experiments show that despite the architectural simplicity, under the right representation, the models are fast and accurate.

2019

pdf bib
Towards Making a Dependency Parser See
Michalina Strzyz | David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We explore whether it is possible to leverage eye-tracking data in an RNN dependency parser (for English) when such information is only available during training - i.e. no aggregated or token-level gaze features are used at inference time. To do so, we train a multitask learning model that parses sentences as sequence labeling and leverages gaze features as auxiliary tasks. Our method also learns to train from disjoint datasets, i.e. it can be used to test whether already collected gaze features are useful to improve the performance on new non-gazed annotated treebanks. Accuracy gains are modest but positive, showing the feasibility of the approach. It can serve as a first step towards architectures that can better leverage eye-tracking data or other complementary information available only for training sentences, possibly leading to improvements in syntactic parsing.

pdf bib
HEAD-QA: A Healthcare Dataset for Complex Reasoning
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present HEAD-QA, a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans. We then consider monolingual (Spanish) and cross-lingual (to English) experiments with information retrieval and neural techniques. We show that: (i) HEAD-QA challenges current methods, and (ii) the results lag well behind human performance, demonstrating its usefulness as a benchmark for future work.

pdf bib
Sequence Labeling Parsing by Learning across Representations
Michalina Strzyz | David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions.To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm. Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed. The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform single-task ones by 1.05 F1 points, and for dependency parsing by 0.62 UAS points.

pdf bib
Artificially Evolved Chunks for Morphosyntactic Analysis
Mark Anderson | David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 18th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2019)

pdf bib
Viable Dependency Parsing as Sequence Labeling
Michalina Strzyz | David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, results suggested that the technique was impractical. We show instead that with a conventional BILSTM-based model it is possible to obtain fast and accurate parsers. These parsers are conceptually simple, not needing traditional parsing algorithms or auxiliary structures. However, experiments on the PTB and a sample of UD treebanks show that they provide a good speed-accuracy tradeoff, with results competitive with more complex approaches.

pdf bib
Harry Potter and the Action Prediction Challenge from Natural Language
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We explore the challenge of action prediction from textual descriptions of scenes, a testbed to approximate whether text inference can be used to predict upcoming actions. As a case of study, we consider the world of the Harry Potter fantasy novels and inferring what spell will be cast next given a fragment of a story. Spells act as keywords that abstract actions (e.g. ‘Alohomora’ to open a door) and denote a response to the environment. This idea is used to automatically build HPAC, a corpus containing 82,836 samples and 85 actions. We then evaluate different baselines. Among the tested models, an LSTM-based approach obtains the best performance for frequent actions and large scene descriptions, but approaches such as logistic regression behave well on infrequent actions.

pdf bib
Better, Faster, Stronger Sequence Tagging Constituent Parsers
David Vilares | Mostafa Abdou | Anders Søgaard
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and use multi-task learning to jointly learn to predict sublabels. Finally, we mitigate issues from greedy decoding through auxiliary losses and sentence-level fine-tuning with policy gradient. Combining these techniques, we clearly surpass the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebanks, and reduce their parsing time even further. On the SPMRL datasets, we observe even greater improvements across the board, including a new state of the art on Basque, Hebrew, Polish and Swedish.

2018

pdf bib
A Transition-Based Algorithm for Unrestricted AMR Parsing
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64%, and showing good behavior on reentrant edges.

pdf bib
Constituent Parsing as Sequence Labeling
Carlos Gómez-Rodríguez | David Vilares
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We introduce a method to reduce constituent parsing to sequence labeling. For each word wt, it generates a label that encodes: (1) the number of ancestors in the tree that the words wt and wt+1 have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.

pdf bib
Grounding the Semantics of Part-of-Day Nouns Worldwide using Twitter
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media

The usage of part-of-day nouns, such as ‘night’, and their time-specific greetings (‘good night’), varies across languages and cultures. We show the possibilities that Twitter offers for studying the semantics of these terms and its variability between countries. We mine a worldwide sample of multilingual tweets with temporal greetings, and study how their frequencies vary in relation with local time. The results provide insights into the semantics of these temporal expressions and the cultural and sociological factors influencing their usage.

pdf bib
Transition-based Parsing with Lighter Feed-Forward Networks
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)

We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.

2017

pdf bib
A non-projective greedy dependency parser with bidirectional LSTMs
David Vilares | Carlos Gómez-Rodríguez
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

The LyS-FASTPARSE team present BIST-COVINGTON, a neural implementation of the Covington (2001) algorithm for non-projective dependency parsing. The bidirectional LSTM approach by Kiperwasser and Goldberg (2016) is used to train a greedy parser with a dynamic oracle to mitigate error propagation. The model participated in the CoNLL 2017 UD Shared Task. In spite of not using any ensemble methods and using the baseline segmentation and PoS tagging, the parser obtained good results on both macro-average LAS and UAS in the big treebanks category (55 languages), ranking 7th out of 33 teams. In the all treebanks category (LAS and UAS) we ranked 16th and 12th. The gap between the all and big categories is mainly due to the poor performance on four parallel PUD treebanks, suggesting that some ‘suffixed’ treebanks (e.g. Spanish-AnCora) perform poorly on cross-treebank settings, which does not occur with the corresponding ‘unsuffixed’ treebank (e.g. Spanish). By changing that, we obtain the 11th best LAS among all runs (official and unofficial). The code is made available at https://github.com/CoNLL-UD-2017/LyS-FASTPARSE

pdf bib
Towards Syntactic Iberian Polarity Classification
David Vilares | Marcos Garcia | Miguel A. Alonso | Carlos Gómez-Rodríguez
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

Lexicon-based methods using syntactic rules for polarity classification rely on parsers that are dependent on the language and on treebank guidelines. Thus, rules are also dependent and require adaptation, especially in multilingual scenarios. We tackle this challenge in the context of the Iberian Peninsula, releasing the first symbolic syntax-based Iberian system with rules shared across five official languages: Basque, Catalan, Galician, Portuguese and Spanish. The model is made available.

pdf bib
Detecting Perspectives in Political Debates
David Vilares | Yulan He
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We explore how to detect people’s perspectives that occupy a certain proposition. We propose a Bayesian modelling approach where topics (or propositions) and their associated perspectives (or viewpoints) are modeled as latent variables. Words associated with topics or perspectives follow different generative routes. Based on the extracted perspectives, we can extract the top associated sentences from text to generate a succinct summary which allows a quick glimpse of the main viewpoints in a document. The model is evaluated on debates from the House of Commons of the UK Parliament, revealing perspectives from the debates without the use of labelled data and obtaining better results than previous related solutions under a variety of evaluations.

2016

pdf bib
EN-ES-CS: An English-Spanish Code-Switching Twitter Corpus for Multilingual Sentiment Analysis
David Vilares | Miguel A. Alonso | Carlos Gómez-Rodríguez
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

Code-switching texts are those that contain terms in two or more different languages, and they appear increasingly often in social media. The aim of this paper is to provide a resource to the research community to evaluate the performance of sentiment classification techniques on this complex multilingual environment, proposing an English-Spanish corpus of tweets with code-switching (EN-ES-CS CORPUS). The tweets are labeled according to two well-known criteria used for this purpose: SentiStrength and a trinary scale (positive, neutral and negative categories). Preliminary work on the resource is already done, providing a set of baselines for the research community.

pdf bib
One model, two languages: training bilingual parsers with harmonized treebanks
David Vilares | Carlos Gómez-Rodríguez | Miguel A. Alonso
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
LyS at SemEval-2016 Task 4: Exploiting Neural Activation Values for Twitter Sentiment Classification and Quantification
David Vilares | Yerai Doval | Miguel A. Alonso | Carlos Gómez-Rodríguez
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

2015

pdf bib
Sentiment Analysis on Monolingual, Multilingual and Code-Switching Twitter Corpora
David Vilares | Miguel A. Alonso | Carlos Gómez-Rodríguez
Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

2014

pdf bib
LyS: Porting a Twitter Sentiment Analysis Approach from Spanish to English
David Vilares | Miguel Hermo | Miguel A. Alonso | Carlos Gómez-Rodríguez | Yerai Doval
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)