JavaScript is disabled for your browser. Some features of this site may not work without it.
Density Representations for Words and Hierarchical Data

Author
Athiwaratkun, Praphruetpong (Ben)
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.
Date Issued
2019-05-30Subject
Artificial intelligence; Probabilistic embeddings; Word embeddings
Committee Chair
Wilson, Andrew Gordon
Committee Member
Cardie, Claire T.; Mimno, David
Degree Discipline
Statistics
Degree Name
Ph.D., Statistics
Degree Level
Doctor of Philosophy
Rights
Attribution 4.0 International
Rights URI
Type
dissertation or thesis
Except where otherwise noted, this item's license is described as Attribution 4.0 International