Back to search

Cornell University

Deep Sequential and Structural Neural Models of Compositionality

Abstract

dc:description.abstract

Recent advances in deep learning have provided fruitful applications for natural language processing (NLP) tasks. One key advance was the invention of word vectors, representing every word in a dense, low-dimensional vector space. Even though word vectors provide very strong results for word level NLP tasks, producing appropriate representation for phrases and sentences is still an open research problem. In this dissertation, we focus on compositional approaches to representation learning. In particular, we employ the notions of compositionality in which the sequence or structure information is utilized, via recurrent or recursive neural networks. We investigate the effectiveness of such approaches for specific natural language understanding tasks including opinion mining and sentiment analysis, and extend some of the approaches to provide better representation hierarchies. In particular, we propose two novel variants: bidirectional recursive neural networks, which are capable of producing context-dependent structural representations and deep recursive neural networks, which provide representation hierarchies in the structural setting. Additionally, we qualitatively investigate such models, and describe how they relate to alternative compositional approaches. Finally, we discuss challenges in interpretation and understanding of compositional neural models, propose simple tools for visualization, and perform exploratory analyses over features learned by such a model.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2017

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Irsoy, Ozan
Chair dc:contributor.chair
  • Cardie, Claire T
Committee members dc:contributor.committeemember
  • Woodard, Dawn B.
  • Kleinberg, Robert David

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
9906139
Dc Identifier Other
ProQuest Submission ID: 10131
ProQuest Publication ID: 10253515

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Irsoy, Ozan. Deep Sequential and Structural Neural Models of Compositionality. Doctor of Philosophy thesis, Cornell University, 2017. https://hdl.handle.net/1813/47892