Story Cloze Task: UW NLP System

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

doi:10.18653/v1/W17-0907

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 proceeding › Conference contribution › peer-review

33 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 language	English
Title of host publication	LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	52-55
Number of pages	4
ISBN (Electronic)	9781945626401
DOIs	https://doi.org/10.18653/v1/W17-0907
State	Published - 2017
Externally published	Yes
Event	2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017 - Valencia, Spain Duration: 3 Apr 2017 → …

Publication series

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

Conference

Conference	2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → …

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics

Access to Document

10.18653/v1/W17-0907

Cite this

Schwartz, R., Sap, M., Konstas, I., Zilles, L., Choi, Y., & Smith, N. A. (2017). Story Cloze Task: UW NLP System. In LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop (pp. 52-55). (LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/W17-0907

Schwartz, Roy ; Sap, Maarten ; Konstas, Ioannis et al. / Story Cloze Task : UW NLP System. LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. pp. 52-55 (LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop).

@inproceedings{90b6f1e79a6e41819353a809cc143af7,

title = "Story Cloze Task: UW NLP System",

abstract = "This paper describes University of Washington NLP{\textquoteright}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).",

author = "Roy Schwartz and Maarten Sap and Ioannis Konstas and Leila Zilles and Yejin Choi and Smith, \{Noah A.\}",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics; 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017 ; Conference date: 03-04-2017",

year = "2017",

doi = "10.18653/v1/W17-0907",

language = "אנגלית",

series = "LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop",

publisher = "Association for Computational Linguistics (ACL)",

pages = "52--55",

booktitle = "LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop",

address = "ארצות הברית",

}

Schwartz, R, Sap, M, Konstas, I, Zilles, L, Choi, Y & Smith, NA 2017, Story Cloze Task: UW NLP System. in LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop. LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 52-55, 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017, Valencia, Spain, 3/04/17. https://doi.org/10.18653/v1/W17-0907

Story Cloze Task: UW NLP System. / Schwartz, Roy; Sap, Maarten; Konstas, Ioannis et al.
LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. p. 52-55 (LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Story Cloze Task

T2 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, LSDSem 2017

AU - Schwartz, Roy

AU - Sap, Maarten

AU - Konstas, Ioannis

AU - Zilles, Leila

AU - Choi, Yejin

AU - Smith, Noah A.

PY - 2017

Y1 - 2017

N2 - 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).

AB - 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).

UR - https://www.scopus.com/pages/publications/85122971607

U2 - 10.18653/v1/W17-0907

DO - 10.18653/v1/W17-0907

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85122971607

T3 - LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop

SP - 52

EP - 55

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

PB - Association for Computational Linguistics (ACL)

Y2 - 3 April 2017

ER -

Schwartz R, Sap M, Konstas I, Zilles L, Choi Y, Smith NA. Story Cloze Task: UW NLP System. In LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2017. p. 52-55. (LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop). doi: 10.18653/v1/W17-0907

Story Cloze Task: UW NLP System

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this