Class-based word sense induction for dot-type nominals

Citació

  • Romeo L, Martínez Alonso H, Bel N. Class-based word sense induction for dot-type nominals. In: Saurí R, Calzolari N, Huang C-R, Lenci A, Monachini M, Pustejovsky J, editors. Proceedings of the 6th International Conference on Generative Approaches to the Lexicon (GL2013); 2013 Sep 24-25; Pisa, Italy. Stroudsburg (USA): Association for Computational Linguistics (ACL); 2013. p. 76-84.

Enllaç permanent

Descripció

  • Resum

    This paper describes an effort to capture the sense alternation of dot-type nominals using Word Sense Induction (WSI). We propose dot-type nominals generate more semantically consistent groupings when clustered into more than two clusters, accounting for literal, metonymic and underspecified senses. Using a class-based approach, we replace individual lemmas with a placeholder representing the entire dot type, which also compensates for data sparsity. Although the distributional evidence does not motivate an individual cluster for each sense, we discuss how our results empirically support theoretical proposals regarding dot types.
  • Descripció

    Comunicació presentada a: 6th International Conference on Generative Approaches to the Lexicon, celebrada a Pisa, Itàlia, del 24 al 25 de setembre del 2013.
  • Mostra el registre complet