Back to search

Cornell University

Density Representations for Words and Hierarchical Data

Abstract

dc:description.abstract

We demonstrate the benefits of probabilistic representations due to their expressiveness which allows for flexible representations, their ability of capture uncertainty, and their interpretable geometric structures that are suitable for modeling hierarchical data. We show that multimodal densities can be effectively used to represent words in natural text, capturing possibly multiple meanings and their nuances. Probability densities also have natural geometric structures which can be used to represent hierarchies among entities through the concept of encapsulation; that is, dispersed distributions are generic entities that encompass more specific ones. We show an effective approach to train such density embeddings by penalizing order violations which are defined through on asymmetric divergences of probability densities.

Degree

thesis:*
Name thesis:degree_name
Ph.D., Statistics
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Statistics
Grantor
Cornell University
Year dc:date.issued
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Athiwaratkun, Praphruetpong (Ben)
Chair dc:contributor.chair
  • Wilson, Andrew Gordon
Committee members dc:contributor.committeemember
  • Cardie, Claire T.
  • Mimno, David

Subjects

dc:subject × 3

Rights

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

Identifiers

dc:identifier.*
Dc Identifier Bibid
11050402
Dc Identifier Other
ProQuest Submission ID: 11382
ProQuest Publication ID: 13879485

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

Athiwaratkun, Praphruetpong (Ben). Density Representations for Words and Hierarchical Data. Doctor of Philosophy thesis, Cornell University, 2019. https://hdl.handle.net/1813/67420