Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding

Yun Nung Chen, Dilek Hakkani-Tur, Gokan Tur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent works showed the trend of leveraging web-scaled structured semantic knowledge resources such as Freebase for open domain spoken language understanding (SLU). Knowledge graphs provide sufficient but ambiguous relations for the same entity, which can be used as statistical background knowledge to infer possible relations for interpretation of user utterances. This paper proposes an approach to capture the relational surface forms by mapping dependency-based contexts of entities from the text domain to the spoken domain. Relational surface forms are learned from dependency-based entity embeddings, which encode the contexts of entities from dependency trees in a deep learning model. The derived surface forms carry functional dependency to the entities and convey the explicit expression of relations. The experiments demonstrate the efficiency of leveraging derived relational surface forms as local cues together with prior background knowledge.

Original languageEnglish (US)
Title of host publication2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages242-247
Number of pages6
ISBN (Electronic)9781479971299
DOIs
StatePublished - Apr 1 2014
Externally publishedYes
Event2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - South Lake Tahoe, United States
Duration: Dec 7 2014Dec 10 2014

Publication series

Name2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings

Conference

Conference2014 IEEE Workshop on Spoken Language Technology, SLT 2014
Country/TerritoryUnited States
CitySouth Lake Tahoe
Period12/7/1412/10/14

Keywords

  • Entity embeddings
  • Relation detection
  • Semantic knowledge graph
  • Spoken dialogue systems (SDS)
  • Spoken language understanding (SLU)

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding'. Together they form a unique fingerprint.

Cite this