Dependency Parsing Domain Adaptation Using Transductive SVM

Antonio Valerio Miceli-Barone; Giuseppe Attardi

Dependency Parsing Domain Adaptation Using Transductive SVM

Antonio Valerio Miceli-Barone, Giuseppe Attardi

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

Abstract

Dependency Parsing domain adaptation involves adapting a dependency parser, trained on an annotated corpus from a given domain (e.g., newspaper articles), to work on a different target domain (e.g., legal documents), given only an unannotated corpus from the target domain.

We present a shift/reduce dependency parser that can handle unlabeled sentences in its training set using a transductive SVM as its action selection classifier.

We illustrate the the experiments we performed with this parser on a domain adaptation task for the Italian language.

Original language	English
Title of host publication	Proceedings of the Joint Workshop on Unsupervised and Semi-Supervised Learning in NLP
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	55-59
Number of pages	5
Publication status	Published - 2012

Publication series

Name	ROBUS-UNSUP '12
Publisher	Association for Computational Linguistics

Access to Document

http://dl.acm.org/citation.cfm?id=2389961.2389968

Cite this

@inproceedings{f2f4a45e537f4c079281e47e8dcd827c,

title = "Dependency Parsing Domain Adaptation Using Transductive SVM",

abstract = "Dependency Parsing domain adaptation involves adapting a dependency parser, trained on an annotated corpus from a given domain (e.g., newspaper articles), to work on a different target domain (e.g., legal documents), given only an unannotated corpus from the target domain.We present a shift/reduce dependency parser that can handle unlabeled sentences in its training set using a transductive SVM as its action selection classifier.We illustrate the the experiments we performed with this parser on a domain adaptation task for the Italian language.",

author = "Miceli-Barone, {Antonio Valerio} and Giuseppe Attardi",

year = "2012",

language = "English",

series = "ROBUS-UNSUP '12",

publisher = "Association for Computational Linguistics",

pages = "55--59",

booktitle = "Proceedings of the Joint Workshop on Unsupervised and Semi-Supervised Learning in NLP",

}

Dependency Parsing Domain Adaptation Using Transductive SVM. / Miceli-Barone, Antonio Valerio; Attardi, Giuseppe.

Proceedings of the Joint Workshop on Unsupervised and Semi-Supervised Learning in NLP. Stroudsburg, PA, USA : Association for Computational Linguistics, 2012. p. 55-59 (ROBUS-UNSUP '12).

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

TY - GEN

T1 - Dependency Parsing Domain Adaptation Using Transductive SVM

AU - Miceli-Barone, Antonio Valerio

AU - Attardi, Giuseppe

PY - 2012

Y1 - 2012

N2 - Dependency Parsing domain adaptation involves adapting a dependency parser, trained on an annotated corpus from a given domain (e.g., newspaper articles), to work on a different target domain (e.g., legal documents), given only an unannotated corpus from the target domain.We present a shift/reduce dependency parser that can handle unlabeled sentences in its training set using a transductive SVM as its action selection classifier.We illustrate the the experiments we performed with this parser on a domain adaptation task for the Italian language.

AB - Dependency Parsing domain adaptation involves adapting a dependency parser, trained on an annotated corpus from a given domain (e.g., newspaper articles), to work on a different target domain (e.g., legal documents), given only an unannotated corpus from the target domain.We present a shift/reduce dependency parser that can handle unlabeled sentences in its training set using a transductive SVM as its action selection classifier.We illustrate the the experiments we performed with this parser on a domain adaptation task for the Italian language.

M3 - Conference contribution

T3 - ROBUS-UNSUP '12

SP - 55

EP - 59

BT - Proceedings of the Joint Workshop on Unsupervised and Semi-Supervised Learning in NLP

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

ER -

Dependency Parsing Domain Adaptation Using Transductive SVM

Abstract

Publication series

Access to Document

Fingerprint

Cite this