Learning reliability of parses for domain adaptation of dependency parsing

Daisuke Kawahara; Kiyotaka Uchimoto

Learning reliability of parses for domain adaptation of dependency parsing

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

Abstract

The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.

Original language	English
Title of host publication	IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	709-714
Number of pages	6
ISBN (Electronic)	9780000000002
Publication status	Published - 2008
Externally published	Yes
Event	3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 - Hyderabad, India Duration: 2008 Jan 7 → 2008 Jan 12

Publication series

Name	IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
Volume	2

Conference

Conference	3rd International Joint Conference on Natural Language Processing, IJCNLP 2008
Country/Territory	India
City	Hyderabad
Period	08/1/7 → 08/1/12

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

Kawahara, D., & Uchimoto, K. (2008). Learning reliability of parses for domain adaptation of dependency parsing. In IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference (pp. 709-714). (IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference; Vol. 2). Association for Computational Linguistics (ACL).

Learning reliability of parses for domain adaptation of dependency parsing. / Kawahara, Daisuke; Uchimoto, Kiyotaka.

IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2008. p. 709-714 (IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference; Vol. 2).

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

Kawahara, D & Uchimoto, K 2008, Learning reliability of parses for domain adaptation of dependency parsing. in IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference, vol. 2, Association for Computational Linguistics (ACL), pp. 709-714, 3rd International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, 08/1/7.

Kawahara D, Uchimoto K. Learning reliability of parses for domain adaptation of dependency parsing. In IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2008. p. 709-714. (IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference).

Kawahara, Daisuke ; Uchimoto, Kiyotaka. / Learning reliability of parses for domain adaptation of dependency parsing. IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2008. pp. 709-714 (IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference).

@inproceedings{7f399c2765eb4921b83c217395db9c90,

title = "Learning reliability of parses for domain adaptation of dependency parsing",

abstract = "The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.",

author = "Daisuke Kawahara and Kiyotaka Uchimoto",

note = "Publisher Copyright: {\textcopyright} 2008 IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. All rights reserved.; 3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 ; Conference date: 07-01-2008 Through 12-01-2008",

year = "2008",

language = "English",

series = "IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference",

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

pages = "709--714",

booktitle = "IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Learning reliability of parses for domain adaptation of dependency parsing

AU - Kawahara, Daisuke

AU - Uchimoto, Kiyotaka

PY - 2008

Y1 - 2008

N2 - The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.

AB - The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.

UR - http://www.scopus.com/inward/record.url?scp=85120180072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85120180072&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85120180072

T3 - IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference

SP - 709

EP - 714

BT - IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 3rd International Joint Conference on Natural Language Processing, IJCNLP 2008

Y2 - 7 January 2008 through 12 January 2008

ER -

Learning reliability of parses for domain adaptation of dependency parsing

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this