Skip to main navigation Skip to search Skip to main content

VigNet: Grounding Language in Graphics using Frame Semantics

  • Columbia University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

This paper introduces Vignette Semantics, a lexical semantic theory based on Frame Semantics that represents conceptual and graphical relations. We also describe a lexical resource that implements this theory, VigNet, and its application in text-To-scene generation.

Original languageEnglish
Title of host publicationWorkshop on Relational Models of Semantics, RELMS 2011 at the 49th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, ACL-HLT 2011 - Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages28-36
Number of pages9
ISBN (Electronic)9781932432985
StatePublished - 2011
EventACL 2011 Workshop on Relational Models of Semantics, RELMS 2011 - Portland, United States
Duration: Jun 23 2011 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

ConferenceACL 2011 Workshop on Relational Models of Semantics, RELMS 2011
Country/TerritoryUnited States
CityPortland
Period06/23/11 → …

Fingerprint

Dive into the research topics of 'VigNet: Grounding Language in Graphics using Frame Semantics'. Together they form a unique fingerprint.

Cite this