Determining if this word is used like that word: predicting usage similarity with supervised and unsupervised approaches

Simple item page
dc.contributor.advisorCook, Paul
dc.contributor.authorKing, Milton
dc.date.accessioned2023-03-01T16:16:20Z
dc.date.available2023-03-01T16:16:20Z
dc.date.issued2017
dc.date.updated2019-05-17T00:00:00Z
dc.description.abstractDetermining the meaning of a word in context is an important task for a variety of natural language processing applications such as translating between languages, summarizing paragraphs, and phrase completion. Usage similarity (USim) is an approach to describe the meaning of a word in context that does not rely on a sense inventory -- a set of dictionary-like definitions. Instead, pairs of usages of a target word are rated in terms of their similarity on a scale. In this thesis, we evaluate unsupervised approaches to USim based on embeddings for words, contexts, and sentences, and achieve state-of-the-art results over two USim datasets. We further consider supervised approaches to USim, and find that they can increase the performance of our models. We look into a more detailed evaluation, observing the performance on different parts-of-speech as well as the change in performance when using different features. Our models also do competitively well in two word sense induction tasks, which involve clustering instances of a word based on the meaning of the word in context.
dc.description.copyright©Milton King, 2017
dc.description.noteM.C.S. University of New Brunswick, Faculty of Computer Science, 2017.
dc.formattext/xml
dc.format.extentviii, 75 pages
dc.format.mediumelectronic
dc.identifier.otherThesis 10088
dc.identifier.urihttps://unbscholar.lib.unb.ca/handle/1882/13204
dc.language.isoen_CA
dc.publisherUniversity of New Brunswick
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subject.classificationWord Sense Disambiguation.
dc.subject.disciplineComputer Science
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshLearning classifier systems.
dc.subject.lcshSemantics -- Data processing.
dc.subject.lcshAmbiguity -- Data processing.
dc.subject.lcshLanguages, Modern -- Idioms -- Data processing.
dc.subject.lcshLanguages, Modern -- Terms and phrases -- Data processing.
dc.subject.lcshWord recognition -- Data processing.
dc.subject.lcshSupervised learning (Machine learning)
dc.subject.lcshDiscourse analysis -- Data processing.
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshComputational linguistics.
dc.titleDetermining if this word is used like that word: predicting usage similarity with supervised and unsupervised approaches
dc.typemaster thesis
thesis.degree.disciplineComputer Science
thesis.degree.fullnameMaster of Computer Science
thesis.degree.grantorUniversity of New Brunswick
thesis.degree.levelmasters
thesis.degree.nameM.C.S.

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
item.pdf
Size:
593.74 KB
Format:
Adobe Portable Document Format
Download

Collections

Open Theses & Dissertations