eCommons

 

Density Representations for Words and Hierarchical Data

Other Titles

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.

Journal / Series

Volume & Issue

Description

Sponsorship

Date Issued

2019-05-30

Publisher

Keywords

Artificial intelligence; Probabilistic embeddings; Word embeddings

Location

Effective Date

Expiration Date

Sector

Employer

Union

Union Local

NAICS

Number of Workers

Committee Chair

Wilson, Andrew Gordon

Committee Co-Chair

Committee Member

Cardie, Claire T.
Mimno, David

Degree Discipline

Statistics

Degree Name

Ph.D., Statistics

Degree Level

Doctor of Philosophy

Related Version

Related DOI

Related To

Related Part

Based on Related Item

Has Other Format(s)

Part of Related Item

Related To

Related Publication(s)

Link(s) to Related Publication(s)

References

Link(s) to Reference(s)

Previously Published As

Government Document

ISBN

ISMN

ISSN

Other Identifiers

Rights

Attribution 4.0 International

Types

dissertation or thesis

Accessibility Feature

Accessibility Hazard

Accessibility Summary

Link(s) to Catalog Record