Recent Submissions

  • Sequence Tagging for Fast Dependency Parsing 

    Strzyz, Michalina; Vilares, David; Gómez-Rodríguez, Carlos (2019)
    [Abstract] Dependency parsing has been built upon the idea of using parsing methods based on shift-reduce or graph-based algorithms in order to identify binary dependency relations between the words in a sentence. In this ...
  • Cognitive Constraints Built into Formal Grammars: Implications for Language Evolution 

    Gómez-Rodríguez, Carlos; Christiansen, Morten H.; Ferrer-i-Cancho, Ramon (Ravignani, A., Barbieri, C., Martins, M., Flaherty, M., Jadoul, Y., Lattenkamp, E., Little, H., Mudd, K., Verhoef, T., 2020-04-17)
    [Abstract] We study the validity of the cognitive independence assumption using an ensemble of artificial syntactic structures from various classes of dependency grammars. Our findings show that memory limitations have ...
  • Parsing as Pretraining 

    Vilares, David; Strzyz, Michalina; Søgaard, Anders; Gómez-Rodríguez, Carlos (2020)
    [Abstract] Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups ...
  • Uma Utilidade para o Reconhecimento de Topónimos em Documentos Medievais 

    Canosa, Xavier; Gamallo, Pablo; Varela, Xavier; Martínez Lema, Paulo; García, Marcos; Taboada, José Angel (Universidade do Minho, 2019)
    [Resumo] Este artigo apresenta o método de construçao duma ferramenta para a anotaçao de entidades geográficas mencionadas em textos medievais. A nova ferramenta foi desenvolvida a partir dos módulos de língua contemporanea ...
  • Building a New Sentiment Analysis Dataset for Uzbek Language and Creating Baseline Models 

    Kuriyozov, Elmurod; Matlatipov, Sanatbek (2019-08-02)
    [Abstract] Making natural language processing technologies available for low-resource languages is an important goal to improve the access to technology in their communities of speakers. In this paper, we provide the first ...

View more