Hierarchical density order embeddings

Ben Athiwaratkun, Andrew Gordon Wilson

Research output: Contribution to conferencePaperpeer-review

Abstract

By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty (Vilnis & McCallum, 2014; Athiwaratkun & Wilson, 2017). The uncertainty information can be particularly meaningful in capturing entailment relationships – whereby general words such as “entity” correspond to broad distributions that encompass more specific words such as “animal” or “instrument”. We introduce density order embeddings, which learn hierarchical representations through encapsulation of probability distributions. In particular, we propose simple yet effective loss functions and distance metrics, as well as graph-based schemes to select negative samples to better learn hierarchical probabilistic representations. Our approach provides state-of-the-art performance on the WORDNET hypernym relationship prediction task and the challenging HYPERLEX lexical entailment dataset – while retaining a rich and interpretable probabilistic representation.

Original languageEnglish (US)
StatePublished - Jan 1 2018
Event6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada
Duration: Apr 30 2018May 3 2018

Conference

Conference6th International Conference on Learning Representations, ICLR 2018
CountryCanada
CityVancouver
Period4/30/185/3/18

ASJC Scopus subject areas

  • Language and Linguistics
  • Education
  • Computer Science Applications
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Hierarchical density order embeddings'. Together they form a unique fingerprint.

Cite this