Augmenting Context with Glosses for Lexical Semantics

• Author / Creator

  Omarov, Talgat

• Computational lexical semantics is a subfield of natural language processing (NLP) that deals with the study of meaning in language at the level of individual words or phrases using computational models and algorithms. Despite the recent success of large language models and contextualized word embeddings in solving lexical semantic tasks, traditional lexical resources such as WordNet remain critical in providing comprehensive coverage of infrequent word meanings and providing additional information on word definitions, usage examples, and semantic relationships among senses. In this thesis, we explore the idea of leveraging information retrieved from lexical resources to solve lexical semantic tasks. In particular, we demonstrate that augmenting the input context with glosses retrieved from lexical resources improves the performance on two lexical semantic tasks: lexical substitution and idiomaticity detection. The results confirm the utility of additional lexical information and provide empirical evidence supporting our claims.

• Subjects / Keywords

  • lexical semantics
  • idiomaticity detection
  • lexical substitution

• Graduation date

  Fall 2023

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-15wv-hf34

• 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.