Japanese zero reference resolution considering exophora and author/reader mentions

Masatsugu Hangyo, Daisuke Kawahara, Sadao Kurohashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

In Japanese, zero references often occur and many of them are categorized into zero ex-ophora, in which a referent is not mentioned in the document. However, previous studies have focused on only zero endophora, in which a referent explicitly appears. We present a zero reference resolution model considering zero exophora and author/reader of a document. To deal with zero exophora, our model adds pseudo entities corresponding to zero exophora to candidate referents of zero pronouns. In addition, we automatically detect mentions that refer to the author and reader of a document by using lexico-syntactic patterns. We represent their particular behavior in a discourse as a feature vector of a machine learning model. The experimental results demonstrate the effectiveness of our model for not only zero exophora but also zero endophora.

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)
Pages924-934
Number of pages11
ISBN (Electronic)9781937284978
Publication statusPublished - Jan 1 2013
Event2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013 - Seattle, United States
Duration: Oct 18 2013Oct 21 2013

Other

Other2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013
CountryUnited States
CitySeattle
Period10/18/1310/21/13

Fingerprint

Syntactics
Learning systems

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Information Systems
  • Computer Vision and Pattern Recognition

Cite this

Hangyo, M., Kawahara, D., & Kurohashi, S. (2013). Japanese zero reference resolution considering exophora and author/reader mentions. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 924-934). Association for Computational Linguistics (ACL).

Japanese zero reference resolution considering exophora and author/reader mentions. / Hangyo, Masatsugu; Kawahara, Daisuke; Kurohashi, Sadao.

EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. p. 924-934.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hangyo, M, Kawahara, D & Kurohashi, S 2013, Japanese zero reference resolution considering exophora and author/reader mentions. in EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 924-934, 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Seattle, United States, 10/18/13.
Hangyo M, Kawahara D, Kurohashi S. Japanese zero reference resolution considering exophora and author/reader mentions. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2013. p. 924-934
Hangyo, Masatsugu ; Kawahara, Daisuke ; Kurohashi, Sadao. / Japanese zero reference resolution considering exophora and author/reader mentions. EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. pp. 924-934
@inproceedings{8ab1ade88589428abd8b3540528d5acf,
title = "Japanese zero reference resolution considering exophora and author/reader mentions",
abstract = "In Japanese, zero references often occur and many of them are categorized into zero ex-ophora, in which a referent is not mentioned in the document. However, previous studies have focused on only zero endophora, in which a referent explicitly appears. We present a zero reference resolution model considering zero exophora and author/reader of a document. To deal with zero exophora, our model adds pseudo entities corresponding to zero exophora to candidate referents of zero pronouns. In addition, we automatically detect mentions that refer to the author and reader of a document by using lexico-syntactic patterns. We represent their particular behavior in a discourse as a feature vector of a machine learning model. The experimental results demonstrate the effectiveness of our model for not only zero exophora but also zero endophora.",
author = "Masatsugu Hangyo and Daisuke Kawahara and Sadao Kurohashi",
year = "2013",
month = "1",
day = "1",
language = "English",
pages = "924--934",
booktitle = "EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Japanese zero reference resolution considering exophora and author/reader mentions

AU - Hangyo, Masatsugu

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In Japanese, zero references often occur and many of them are categorized into zero ex-ophora, in which a referent is not mentioned in the document. However, previous studies have focused on only zero endophora, in which a referent explicitly appears. We present a zero reference resolution model considering zero exophora and author/reader of a document. To deal with zero exophora, our model adds pseudo entities corresponding to zero exophora to candidate referents of zero pronouns. In addition, we automatically detect mentions that refer to the author and reader of a document by using lexico-syntactic patterns. We represent their particular behavior in a discourse as a feature vector of a machine learning model. The experimental results demonstrate the effectiveness of our model for not only zero exophora but also zero endophora.

AB - In Japanese, zero references often occur and many of them are categorized into zero ex-ophora, in which a referent is not mentioned in the document. However, previous studies have focused on only zero endophora, in which a referent explicitly appears. We present a zero reference resolution model considering zero exophora and author/reader of a document. To deal with zero exophora, our model adds pseudo entities corresponding to zero exophora to candidate referents of zero pronouns. In addition, we automatically detect mentions that refer to the author and reader of a document by using lexico-syntactic patterns. We represent their particular behavior in a discourse as a feature vector of a machine learning model. The experimental results demonstrate the effectiveness of our model for not only zero exophora but also zero endophora.

UR - http://www.scopus.com/inward/record.url?scp=84926285037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926285037&partnerID=8YFLogxK

M3 - Conference contribution

SP - 924

EP - 934

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

PB - Association for Computational Linguistics (ACL)

ER -