Back to search

Georgia Institute of Technology

Novel document representations based on labels and sequential information

Abstract

dc:description.abstract

A wide variety of text analysis applications are based on statistical machine learning techniques. The success of those applications is critically affected by how we represent a document. Learning an efficient document representation has two major challenges: sparsity and sequentiality. The sparsity often causes high estimation error, and text's sequential nature, interdependency between words, causes even more complication. This thesis presents novel document representations to overcome the two challenges. First, I employ label characteristics to estimate a compact document representation. Because label attributes implicitly describe the geometry of dense subspace that has substantial impact, I can effectively resolve the sparsity issue while only focusing the compact subspace. Second, while modeling a document as a joint or conditional distribution between words and their sequential information, I can efficiently reflect sequential nature of text in my document representations. Lastly, the thesis is concluded with a document representation that employs both labels and sequential information in a unified formulation. The following four criteria are utilized to evaluate the goodness of representations: how close a representation is to its original data, how strongly a representation can be distinguished from each other, how easy to interpret a representation by a human, and how much computational effort is needed for a representation. While pursuing those good representation criteria, I was able to obtain document representations that are closer to the original data, stronger in discrimination, and easier to be understood than traditional document representations. Efficient computation algorithms make the proposed approaches largely scalable. This thesis examines emotion prediction, temporal emotion analysis, modeling documents with edit histories, locally coherent topic modeling, and text categorization tasks for possible applications.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2015

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kim, Seungyeon
Advisor dc:contributor.advisor
  • Lebanon, Guy
Committee members dc:contributor.committeemember
  • Park, Haesun
  • Essa, Irfan
  • Eisenstein, Jacob
  • Bengio, Samy

Subjects

dc:subject × 9

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/53946

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kim, Seungyeon. Novel document representations based on labels and sequential information. Doctoral thesis, Georgia Institute of Technology, 2015. http://hdl.handle.net/1853/53946