Speech in Parts Understanding and Modelling the Semantic Differences between Words

Abstract

This thesis is about the problem of differences in lexical semantics with a special emphasis on antonymy. It explores part-of-speech as a means to formalize semantic differences computationally, enhance the performance of computational linguistic tasks and aid in the understanding of lexical semantics more broadly. The thesis begins with an overview of how antonymy has been studied within experimental psychology and the major schools of theoretical linguistics as well as a review of the semantic foundations of part-of-speech. It then turns to computational experiments that use part-of-speech as a primitive organizing principle, including a source categorization task and four automatic antonym identification experiments, which with few exceptions, show results that either meet or exceed human performance. The final chapter presents a computational analysis of semantic markedness and the sequence preferences that that antonyms often demonstrate when they co-occur. The theoretical accounts for these observations are evaluated on the basis of corpus statistics and the thesis concludes with some general observations about the usefulness of computational linguistics in the analysis of semantic theories.

Keywords: artificial intelligence, computational linguistics, linguistics, antonymy, part of speech, linear algebra, machine learning, cognitive science, philosophy of language, semantics, large language models