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: Contribution to conference › Paper

33 Citations (Scopus)

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
Pages	52-55
Number of pages	4
DOIs	https://doi.org/10.18653/v1/W17-0907
Publication status	Published - Apr 2017
Event	2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics 2017 - Valencia, Spain Duration: 3 Apr 2017 → 3 Apr 2017

Workshop

Workshop	2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics 2017
Abbreviated title	LSDSEM 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → 3/04/17

Access to Document

10.18653/v1/W17-0907

Cite this

@conference{8b0684d7a48940099f0c09b0d4620332,

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

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).",

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

year = "2017",

month = apr,

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

language = "English",

pages = "52--55",

note = "2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics 2017, LSDSEM 2017 ; Conference date: 03-04-2017 Through 03-04-2017",

}

TY - CONF

T1 - Story Cloze Task : UW NLP System

AU - Schwartz, Roy

AU - Sap, Maarten

AU - Konstas, Ioannis

AU - Zilles, Leila

AU - Choi, Yejin

AU - Smith, Noah A.

PY - 2017/4

Y1 - 2017/4

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).

U2 - 10.18653/v1/W17-0907

DO - 10.18653/v1/W17-0907

M3 - Paper

SP - 52

EP - 55

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

Y2 - 3 April 2017 through 3 April 2017

ER -

Story Cloze Task : UW NLP System

Abstract

Workshop

Access to Document

Fingerprint

Cite this