Back to search

Cornell University

Learning Deep Models with Linguistically-Inspired Structure

Abstract

dc:description.abstract

Many applied machine learning tasks involve structured representations. This is particularly the case in natural language processing (NLP), where the discrete, compositional nature of words and sentences leads to natural combinatorial representations such as trees, sequences, segments, or alignments, among others. It is no surprise that structured output models have been successful and popular in NLP applications since their inception. At the same time, deep, hierarchical neural networks with latent representations are increasingly widely and successfully applied to language tasks. As compositions of differentiable building blocks, deep models conventionally perform smooth, soft computations, resulting in dense hidden representations. In this work, we focus on models with structure and sparsity in both their outputs as well as their latent representations, without sacrificing differentiability for end-to-end gradient-based training. We develop methods for sparse and structured attention mechanisms, for differentiable sparse structure inference, for latent neural network structure, and for sparse structured output prediction. We find our methods to be empirically useful on a wide range of applications including sentiment analysis, natural language inference, neural machine translation, sentence compression, and argument mining.

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
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Niculae, Vlad
Chair dc:contributor.chair
  • Cardie, Claire T.
Committee members dc:contributor.committeemember
  • Haenni, Sabine
  • Sridharan, Karthik

Subjects

dc:subject × 6

Rights

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

Identifiers

dc:identifier.*
Dc Identifier Bibid
10489636
Dc Identifier Other
ProQuest Submission ID: 11047
ProQuest Publication ID: 10928023

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

Niculae, Vlad. Learning Deep Models with Linguistically-Inspired Structure. Doctor of Philosophy thesis, Cornell University, 2018. https://hdl.handle.net/1813/59540