Skip to main navigation Skip to search Skip to main content

Generating coherent event schemas at scale

  • University of Washington

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

97 Scopus citations

Abstract

Chambers and Jurafsky (2009) demonstrated that event schemas can be automatically induced from text corpora. However, our analysis of their schemas identifies several weaknesses, e.g., some schemas lack a common topic and distinct roles are incorrectly mixed into a single actor. It is due in part to their pair-wise representation that treats subject-verb independently from verb-object. This often leads to subject-verb-object triples that are not meaningful in the real-world. We present a novel approach to inducing open-domain event schemas that overcomes these limitations. Our approach uses cooccurrence statistics of semantically typed relational triples, which we call Rel-grams (relational n-grams). In a human evaluation, our schemas outperform Chambers's schemas by wide margins on several evaluation criteria. Both Rel-grams and event schemas are freely available to the research community.

Original languageEnglish
Title of host publicationEMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1721-1731
Number of pages11
ISBN (Electronic)9781937284978
StatePublished - 2013
Event2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013 - Seattle, United States
Duration: Oct 18 2013Oct 21 2013

Publication series

NameEMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conference

Conference2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013
Country/TerritoryUnited States
CitySeattle
Period10/18/1310/21/13

Fingerprint

Dive into the research topics of 'Generating coherent event schemas at scale'. Together they form a unique fingerprint.

Cite this