Generative models for statistical parsing with combinatory categorial grammar

Julia Hockenmaier; Mark Steedman

Generative models for statistical parsing with combinatory categorial grammar

Julia Hockenmaier
, Mark Steedman

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper compares a number of generative probability models for a widecoverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance of 89.9%, comparable to the figures given by Collins (1999) for a linguistically less expressive grammar. In contrast to Gildea (2001), we find a significant improvement from modeling wordword dependencies.

Original language	English (US)
Pages (from-to)	335-342
Number of pages	8
Journal	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2002-July
State	Published - 2002
Externally published	Yes
Event	40th Annual Meeting of the Association for Computational Linguistics, ACL 2002 - Philadelphia, United States Duration: Jul 7 2002 → Jul 12 2002

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Library availability

Discover UIUC Full Text

Cite this

@article{71d3a39cbfc14939bbbf423ff58d96b4,

title = "Generative models for statistical parsing with combinatory categorial grammar",

abstract = "This paper compares a number of generative probability models for a widecoverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance of 89.9\%, comparable to the figures given by Collins (1999) for a linguistically less expressive grammar. In contrast to Gildea (2001), we find a significant improvement from modeling wordword dependencies.",

author = "Julia Hockenmaier and Mark Steedman",

note = "Publisher Copyright: {\textcopyright} 1992 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All rights reserved.; 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002 ; Conference date: 07-07-2002 Through 12-07-2002",

year = "2002",

language = "English (US)",

volume = "2002-July",

pages = "335--342",

journal = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

issn = "0736-587X",

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

}

TY - JOUR

T1 - Generative models for statistical parsing with combinatory categorial grammar

AU - Hockenmaier, Julia

AU - Steedman, Mark

PY - 2002

Y1 - 2002

N2 - This paper compares a number of generative probability models for a widecoverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance of 89.9%, comparable to the figures given by Collins (1999) for a linguistically less expressive grammar. In contrast to Gildea (2001), we find a significant improvement from modeling wordword dependencies.

AB - This paper compares a number of generative probability models for a widecoverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance of 89.9%, comparable to the figures given by Collins (1999) for a linguistically less expressive grammar. In contrast to Gildea (2001), we find a significant improvement from modeling wordword dependencies.

UR - https://www.scopus.com/pages/publications/85149144666

UR - https://www.scopus.com/pages/publications/85149144666#tab=citedBy

M3 - Conference article

AN - SCOPUS:85149144666

SN - 0736-587X

VL - 2002-July

SP - 335

EP - 342

JO - Proceedings of the Annual Meeting of the Association for Computational Linguistics

JF - Proceedings of the Annual Meeting of the Association for Computational Linguistics

T2 - 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002

Y2 - 7 July 2002 through 12 July 2002

ER -

Generative models for statistical parsing with combinatory categorial grammar

Abstract

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this