Home
Resource
Assessing compositionality and linguistic regularities in pretrained language representation models
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(801.41 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Zhu, Xunjie. Assessing compositionality and linguistic regularities in pretrained language representation models. Retrieved from https://doi.org/doi:10.7282/t3-2gfz-r678

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleAssessing compositionality and linguistic regularities in pretrained language representation models
NameZhu, Xunjie (author); Melo, Gerard de (chair); Stratos, Karl (internal member); Abello, James (internal member); Rutgers University; School of Graduate Studies
Date Created2019
Other Date2019-10 (degree)
SubjectComputer Science, Sentence embeddings, Computer vision
Extent1 online resource (vii, 44 pages) : illustrations
DescriptionWhile in computer vision, models pretrained on ImageNet have long been used for transfer learning, in NLP, there have only recently been important breakthroughs in learning pretrained representation models beyond the level of words. The most well-known of these are the BERT and XLNet ones, which rely on a language modeling objective. Despite the strong gains that they enable in a number of downstream tasks, it is not known to what extent the models can be used as sentence embeddings capturing important semantic phenomena such as compositionality and analogy. In this thesis, we propose a method to assess this based on relationships between vectors. We find that the models reflect only some of the properties we consider
NoteM.S.
NoteIncludes bibliographical references
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/t3-2gfz-r678
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024