Neural network-based model for Japanese predicate argument structure analysis

Tomohide Shibata; Daisuke Kawahara; Sadao Kurohashi

doi:10.18653/v1/p16-1117

Neural network-based model for Japanese predicate argument structure analysis

Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi

Linguistic Education

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

13 Citations (Scopus)

Abstract

This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PAS s in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.

Original language	English
Title of host publication	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	1235-1244
Number of pages	10
ISBN (Electronic)	9781510827585
DOIs	https://doi.org/10.18653/v1/p16-1117
Publication status	Published - 2016
Event	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany Duration: Aug 7 2016 → Aug 12 2016

Publication series

Name	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Volume	3

Other

Other	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Country/Territory	Germany
City	Berlin
Period	8/7/16 → 8/12/16

All Science Journal Classification (ASJC) codes

Language and Linguistics
Linguistics and Language

Access to Document

10.18653/v1/p16-1117

Cite this

Shibata, T., Kawahara, D., & Kurohashi, S. (2016). Neural network-based model for Japanese predicate argument structure analysis. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers (pp. 1235-1244). (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 3). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p16-1117

Neural network-based model for Japanese predicate argument structure analysis. / Shibata, Tomohide; Kawahara, Daisuke; Kurohashi, Sadao.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. p. 1235-1244 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 3).

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

Shibata, T, Kawahara, D & Kurohashi, S 2016, Neural network-based model for Japanese predicate argument structure analysis. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers, vol. 3, Association for Computational Linguistics (ACL), pp. 1235-1244, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 8/7/16. https://doi.org/10.18653/v1/p16-1117

Shibata T, Kawahara D, Kurohashi S. Neural network-based model for Japanese predicate argument structure analysis. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL). 2016. p. 1235-1244. (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers). doi: 10.18653/v1/p16-1117

Shibata, Tomohide ; Kawahara, Daisuke ; Kurohashi, Sadao. / Neural network-based model for Japanese predicate argument structure analysis. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. pp. 1235-1244 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers).

@inproceedings{fd31b1b3f5f64746b8f0e6d28f259904,

title = "Neural network-based model for Japanese predicate argument structure analysis",

abstract = "This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PAS s in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.",

author = "Tomohide Shibata and Daisuke Kawahara and Sadao Kurohashi",

note = "Publisher Copyright: {\textcopyright} 2016 Association for Computational Linguistics.; 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

year = "2016",

doi = "10.18653/v1/p16-1117",

language = "English",

series = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",

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

pages = "1235--1244",

booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",

}

TY - GEN

T1 - Neural network-based model for Japanese predicate argument structure analysis

AU - Shibata, Tomohide

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2016

Y1 - 2016

N2 - This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PAS s in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.

AB - This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PAS s in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.

UR - http://www.scopus.com/inward/record.url?scp=85011876465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011876465&partnerID=8YFLogxK

U2 - 10.18653/v1/p16-1117

DO - 10.18653/v1/p16-1117

M3 - Conference contribution

AN - SCOPUS:85011876465

T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

SP - 1235

EP - 1244

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

PB - Association for Computational Linguistics (ACL)

T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016

Y2 - 7 August 2016 through 12 August 2016

ER -

Neural network-based model for Japanese predicate argument structure analysis

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this