Effective self-training for parsing

David McClosky; Eugene Charniak; Mark Johnson

doi:10.3115/1220835.1220855

Effective self-training for parsing

David McClosky^*, Eugene Charniak, Mark Johnson

^*Corresponding author for this work

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

483 Citations (Scopus)

Abstract

We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.

Original language	English
Title of host publication	HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference
Editors	Robert C. Moore, Jeff A. Bilmes, Jennifer Chu-Carroll, Mark Sanderson
Place of Publication	East Stroudsburg, PA
Publisher	Association for Computational Linguistics (ACL)
Pages	152-159
Number of pages	8
ISBN (Electronic)	9781932432626
DOIs	https://doi.org/10.3115/1220835.1220855
Publication status	Published - 2006
Externally published	Yes
Event	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 - New York, NY, United States Duration: 4 Jun 2006 → 9 Jun 2006

Other

Other	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006
Country/Territory	United States
City	New York, NY
Period	4/06/06 → 9/06/06

Access to Document

10.3115/1220835.1220855

Cite this

McClosky, D., Charniak, E., & Johnson, M. (2006). Effective self-training for parsing. In R. C. Moore, J. A. Bilmes, J. Chu-Carroll, & M. Sanderson (Eds.), HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference (pp. 152-159). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1220835.1220855

McClosky, David ; Charniak, Eugene ; Johnson, Mark. / Effective self-training for parsing. HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference. editor / Robert C. Moore ; Jeff A. Bilmes ; Jennifer Chu-Carroll ; Mark Sanderson. East Stroudsburg, PA : Association for Computational Linguistics (ACL), 2006. pp. 152-159

@inproceedings{f491972e7bb049bf93a609d37530f4a7,

title = "Effective self-training for parsing",

abstract = "We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1\%, an absolute 1.1\% improvement (12\% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.",

author = "David McClosky and Eugene Charniak and Mark Johnson",

year = "2006",

doi = "10.3115/1220835.1220855",

language = "English",

pages = "152--159",

editor = "Moore, \{Robert C.\} and Bilmes, \{Jeff A.\} and Jennifer Chu-Carroll and Mark Sanderson",

booktitle = "HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference",

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

note = "2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 ; Conference date: 04-06-2006 Through 09-06-2006",

}

McClosky, D, Charniak, E & Johnson, M 2006, Effective self-training for parsing. in RC Moore, JA Bilmes, J Chu-Carroll & M Sanderson (eds), HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference. Association for Computational Linguistics (ACL), East Stroudsburg, PA, pp. 152-159, 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States, 4/06/06. https://doi.org/10.3115/1220835.1220855

Effective self-training for parsing. / McClosky, David; Charniak, Eugene; Johnson, Mark.
HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference. ed. / Robert C. Moore; Jeff A. Bilmes; Jennifer Chu-Carroll; Mark Sanderson. East Stroudsburg, PA: Association for Computational Linguistics (ACL), 2006. p. 152-159.

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

TY - GEN

T1 - Effective self-training for parsing

AU - McClosky, David

AU - Charniak, Eugene

AU - Johnson, Mark

PY - 2006

Y1 - 2006

N2 - We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.

AB - We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.

UR - https://www.scopus.com/pages/publications/84863411425

U2 - 10.3115/1220835.1220855

DO - 10.3115/1220835.1220855

M3 - Conference proceeding contribution

AN - SCOPUS:84863411425

SP - 152

EP - 159

BT - HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference

A2 - Moore, Robert C.

A2 - Bilmes, Jeff A.

A2 - Chu-Carroll, Jennifer

A2 - Sanderson, Mark

PB - Association for Computational Linguistics (ACL)

CY - East Stroudsburg, PA

T2 - 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006

Y2 - 4 June 2006 through 9 June 2006

ER -

McClosky D, Charniak E, Johnson M. Effective self-training for parsing. In Moore RC, Bilmes JA, Chu-Carroll J, Sanderson M, editors, HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference. East Stroudsburg, PA: Association for Computational Linguistics (ACL). 2006. p. 152-159 doi: 10.3115/1220835.1220855

Effective self-training for parsing

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this