Class-based Word Sense Induction for dot-type nominals

  • Authors
  • Romeo, Lauren; Martínez Alonso, Héctor; Bel Rafecas, Núria
  • UPF authors
  • BEL RAFECAS, NÚRIA;
  • Authors of the book
  • Saurí, R.; Calzolari, N.; Huang, C.R.; Lenci, A.; Monachini, M.; Pustejovsky. J. (ed.)
  • Book title
  • Proceedings of the 6th International Conference on Generative Approaches to the Lexicon. Generative Lexicon and Distributional Semantics
  • Publication year
  • 2013
  • Pages
  • 76-83
  • ISBN
  • 978-1-937284-98
  • Abstract
  • 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.
  • Complete citation
  • Romeo, Lauren; Martínez Alonso, Héctor; Bel Rafecas, Núria. Class-based Word Sense Induction for dot-type nominals. In: Saurí, R.; Calzolari, N.; Huang, C.R.; Lenci, A.; Monachini, M.; Pustejovsky. J. (ed.). Proceedings of the 6th International Conference on Generative Approaches to the Lexicon. Generative Lexicon and Distributional Semantics. 1 ed. 2013. p. 76-83.