• 4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees 

      Gómez-Rodríguez, Carlos; Roca Rodríguez, Diego; Vilares, David (Association for Computational Linguistics, 2023-12)
      [Absctract]: We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word’s label represent (1) whether it ...
    • A non-projective greedy dependency parser with bidirectional LSTMs 

      Vilares, David; Gómez-Rodríguez, Carlos (Association for Computational Linguistics, 2017-08)
      [Abstract]: 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) ...
    • Una aproximación supervisada para la minería de opiniones sobre tuits en español en base a conocimiento lingüístico 

      Vilares, David; Alonso, Miguel A.; Gómez-Rodríguez, Carlos (Sociedad Española para el Procesamiento del Lenguaje Natural, 2013)
      [Resumen]: En este artículo se describe un sistema para la clasificación de la polaridad de tuits escritos en español. Se adopta una aproximación híbrida, que combina conocimiento lingüístico obtenido mediante PLN con ...
    • Clasificación de polaridad en textos con opiniones en español mediante análisis sintáctico de dependencias 

      Vilares, David; Alonso, Miguel A.; Gómez-Rodríguez, Carlos (Sociedad Española para el Procesamiento del Lenguaje Natural, 2013)
      [Resumen]: En este artículo se describe un sistema de minería de opiniones que clasifica la polaridad de textos en español. Se propone una aproximación basada en PLN que conlleva realizar una segmentación, tokenización y ...
    • Cross-lingual Inflection as a Data Augmentation Method for Parsing 

      Muñoz-Ortiz, Alberto; Gómez-Rodríguez, Carlos; Vilares, David (Association for Computational Linguistics, 2022-05)
      [Absctract]: We propose a morphology-based method for low-resource (LR) dependency parsing. We train a morphological inflector for target LR languages, and apply it to related rich-resource (RR) treebanks to create ...
    • Dependency parsing with bottom-up Hierarchical Pointer Networks 

      Fernández-González, Daniel; Gómez-Rodríguez, Carlos (Elsevier, 2023-03)
      [Abstract] Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based ...
    • Increasing NLP Parsing Efficiency with Chunking 

      Anderson, Mark Dáibhidh; Vilares, David (M D P I AG, 2018-09-19)
      [Abstract] We introduce a “Chunk-and-Pass” parsing technique influenced by a psycholinguistic model, where linguistic information is processed not word-by-word but rather in larger chunks of words. We present preliminary ...
    • Multitask Pointer Network for Multi-Representational Parsing 

      Fernández-González, Daniel; Gómez-Rodríguez, Carlos (Elsevier, 2022-01-25)
      [Abstract] Dependency and constituent trees are widely used by many artificial intelligence applications for representing the syntactic structure of human languages. Typically, these structures are separately produced by ...
    • Sequence Labeling Parsing by Learning across Representations 

      Strzyz, Michalina; Vilares, David; Gómez-Rodríguez, Carlos (Association for Computational Linguistics, 2019-07)
      [Absctract]: 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 ...
    • Towards fast natural language parsing: FASTPARSE ERC Starting Grant 

      Gómez-Rodríguez, Carlos (Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), 2017-09)
      [Abstract:] The goal of the FASTPARSE project (Fast Natural Language Parsing for Large-Scale NLP), funded by the European Research Council (ERC), is to achieve a breakthrough in the speed of natural language syntactic ...
    • Universal, unsupervised (rule-based), uncovered sentiment analysis 

      Vilares, David; Gómez-Rodríguez, Carlos; Alonso, Miguel A. (Elsevier, 2017-02)
      [Abstract]: We present a novel unsupervised approach for multilingual sentiment analysis driven by compositional syntax-based rules. On the one hand, we exploit some of the main advantages of unsupervised algorithms: (1) ...
    • Viable Dependency Parsing as Sequence Labeling 

      Strzyz, Michalina; Vilares, David; Gómez-Rodríguez, Carlos (Association for Computational Linguistics (ACL), 2019-06)
      [Abstract]: 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, ...