Frustratingly hard domain adaptation for dependency parsing

Mark Dredze; John Blitzer; Partha Pratim Talukdar; Kuzman Ganchev; João V. Graça; Fernando Pereira

Frustratingly hard domain adaptation for dependency parsing

Mark Dredze, John Blitzer, Partha Pratim Talukdar, Kuzman Ganchev, João V. Graça, Fernando Pereira

Research output: Contribution to conference › Paper › peer-review

Abstract

We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.

Original language	English (US)
Pages	1051-1055
Number of pages	5
State	Published - 2007
Externally published	Yes
Event	2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007 - Prague, Czech Republic Duration: Jun 28 2007 → Jun 28 2007

Conference

Conference	2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007
Country/Territory	Czech Republic
City	Prague
Period	6/28/07 → 6/28/07

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

Frustratingly hard domain adaptation for dependency parsing. / Dredze, Mark; Blitzer, John; Talukdar, Partha Pratim et al.
2007. 1051-1055 Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic.

Research output: Contribution to conference › Paper › peer-review

@conference{22a08b9f561447d5a76f676ad3d7b4ed,

title = "Frustratingly hard domain adaptation for dependency parsing",

abstract = "We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.",

author = "Mark Dredze and John Blitzer and Talukdar, {Partha Pratim} and Kuzman Ganchev and Gra{\c c}a, {Jo{\~a}o V.} and Fernando Pereira",

year = "2007",

language = "English (US)",

pages = "1051--1055",

note = "2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007 ; Conference date: 28-06-2007 Through 28-06-2007",

}

TY - CONF

T1 - Frustratingly hard domain adaptation for dependency parsing

AU - Dredze, Mark

AU - Blitzer, John

AU - Talukdar, Partha Pratim

AU - Ganchev, Kuzman

AU - Graça, João V.

AU - Pereira, Fernando

PY - 2007

Y1 - 2007

N2 - We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.

AB - We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.

UR - http://www.scopus.com/inward/record.url?scp=76649142537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76649142537&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:76649142537

SP - 1051

EP - 1055

T2 - 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007

Y2 - 28 June 2007 through 28 June 2007

ER -

Frustratingly hard domain adaptation for dependency parsing

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this