Lingua e Sociedade da Información (Language in the Information Society) (LYS): Envíos recentes

Mostrando ítems 31-35 de 122

    • Parsing linearizations appreciate PoS tags - but some are fussy about errors 

      Muñoz-Ortiz, Alberto; Anderson, Mark; Vilares, David; Gómez-Rodríguez, Carlos (Association for Computational Linguistics, 2022-11)
      [Absctract]: PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and ...

    • Better, Faster, Stronger Sequence Tagging Constituent Parsers 

      Vilares, David; Abdou, Mostafa; Søgaard, Anders (Association for Computational Linguistics, 2019-06)
      [Absctract]: 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 ...

    • HEAD-QA: A Healthcare Dataset for Complex Reasoning 

      Vilares, David; Gómez-Rodríguez, Carlos (Association for Computational Linguistics, 2019-07)
      [Absctract]: 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 ...

    • A Unifying Theory of Transition-based and Sequence Labeling Parsing 

      Gómez-Rodríguez, Carlos; Strzyz, Michalina; Vilares, David (International Committee on Computational Linguistics, 2020-12)
      [Absctract]: 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 ...

    • Bracketing Encodings for 2-Planar Dependency Parsing 

      Strzyz, Michalina; Vilares, David; Gómez-Rodríguez, Carlos (International Committee on Computational Linguistics, 2020-12)
      [Absctract]: 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 ...