Story Cloze Task: UW NLP System

Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi, Noah A. Smith

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

32 Scopus citations

Abstract

This paper describes University of Washington NLP’s submission for the Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2017) shared task—the Story Cloze Task. Our system is a linear classifier with a variety of features, including both the scores of a neural language model and style features. We report 75.2% accuracy on the task. A further discussion of our results can be found in Schwartz et al. (2017).

Original languageAmerican English
Title of host publicationLSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages52-55
Number of pages4
ISBN (Electronic)9781945626401
StatePublished - 2017
Externally publishedYes
Event2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017 - Valencia, Spain
Duration: 3 Apr 2017 → …

Publication series

NameLSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop

Conference

Conference2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017
Country/TerritorySpain
CityValencia
Period3/04/17 → …

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'Story Cloze Task: UW NLP System'. Together they form a unique fingerprint.

Cite this