Leveraging Translations for Lexical Semantics

  • Author / Creator
    Bao, Hongchang
  • Computational lexical semantics is the study of word meanings which involves algorithms and ontologies. Computation of semantic similarity plays an important role in various applications of natural language processing, including information retrieval, machine translation, and question answering. Most prior work on computing meaning similarity focus on sense definitions or the relational structure of lexical resources. Lexical translations constitute another important component in lexical resources such as BabelNet and CLICS. In this thesis, we explore the idea of leveraging multilingual translations to compute semantic similarity. In particular: (1) we posit and investigate the hypothesis that there are no universal colexifications, (2) propose an algorithm to align concepts across lexical resources, and (3) develop novel approaches to detect sense synonymy across different contexts. Our results in these three tasks confirm the utility of translations in computational lexical semantics.

  • Subjects / Keywords
  • Graduation date
    Spring 2022
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.