Semantic clustering of pivot paraphrases

Marianna Apidianaki (1) , Emilia Verzeni , Diana Mccarthy

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

Paraphrases extracted from parallel corpora by the pivot method (Bannard and Callison-Burch, 2005) constitute a valuable resource for multilingual NLP applications. In this study, we analyse the semantics of unigram pivot paraphrases and use a graph-based sense induction approach to unveil hidden sense distinctions in the paraphrase sets. The comparison of the acquired senses to gold data from the Lexical Substitution shared task (McCarthy and Navigli, 2007) demonstrates that sense distinctions exist in the paraphrase sets and highlights the need for a disambiguation step in applications using this resource.

Mots clés: pivot paraphrasing; sense clustering; parallel corpora

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

Marianna Apidianaki, Emilia Verzeni, Diana Mccarthy. Semantic clustering of pivot paraphrases. International Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland. ⟨hal-01838559⟩