Lexicography as Feature Engineering

DSpace Repository

Show simple item record

dc.contributor.advisor Pustejovsky, James
dc.contributor.author Montoya, Orion
dc.date.accessioned 2017-09-04T13:07:44Z
dc.date.available 2017-09-04T13:07:44Z
dc.date.issued 2017
dc.identifier.uri http://hdl.handle.net/10192/34138
dc.description.abstract Many different techniques can group synonymous words together, but it is much harder to untangle the nuance and emphasis borne by individual members of a synonym set. The distributional hypothesis holds that you may understand a word by the contexts in which it appears. This thesis applies a sort of transposition of the distributional hypothesis to groups of synonyms. I postulate that, by aggregating the differences among the contexts of similar words, one may discover the range of semantic factors borne by a synonym group as a whole, as well as the implications of choosing an individual member of a synset. By applying an analytical framework along these lines to extract semantic factors for set of synonyms, I initially find factors that are of a different sort than the factors used in most decompositional analyses, and see promise in developing the approach further with varying methods of feature extraction.
dc.description.sponsorship Brandeis University, Graduate School of Arts and Sciences
dc.format.mimetype application/pdf
dc.language English
dc.language.iso eng
dc.publisher Brandeis University
dc.relation.ispartofseries Brandeis University Theses and Dissertations
dc.rights Copyright by Orion Montoya 2017
dc.subject lexical semantics
dc.subject lexicography
dc.subject distributional semantics
dc.subject synonymy
dc.subject plesionymy
dc.title Lexicography as Feature Engineering
dc.type Thesis
dc.contributor.department Graduate Program in Computational Linguistics
dc.degree.name MA
dc.degree.level Masters
dc.degree.discipline Computational Linguistics
dc.degree.grantor Brandeis University, Graduate School of Arts and Sciences


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search BIR


Browse

My Account