The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages

David Chiang; Owen Rambow

The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages

David Chiang
, Owen Rambow

Linguistics

Stony Brook University

University of Southern California

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

4 Scopus citations

Abstract

This paper discusses a novel probabilistic synchronous TAG formalism, synchronous Tree Substitution Grammar with sister adjunction (TSG+SA). We use it to parse a language for which there is no training data, by leveraging off a second, related language for which there is abundant training data. The grammar for the resource-rich side is automatically extracted from a treebank; the grammar on the resource-poor side and the synchronization are created by handwritten rules. Our approach thus represents a combination of grammar-based and empirical natural language processing. We discuss the approach using the example of Levantine Arabic and Standard Arabic. c2006 Association for Computational Linguistics.

Original language	English
Title of host publication	COLING/ACL 2006 - TAG+8
Subtitle of host publication	8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	1-8
Number of pages	8
ISBN (Electronic)	193243285X, 9781932432855
State	Published - 2006
Event	8th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG 2006, co-located with COLING/ACL 2006 - Sydney, Australia Duration: Jul 15 2006 → Jul 16 2006

Publication series

Name	COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop

Conference

Conference	8th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG 2006, co-located with COLING/ACL 2006
Country/Territory	Australia
City	Sydney
Period	07/15/06 → 07/16/06

Cite this

Chiang, D., & Rambow, O. (2006). The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages. In COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop (pp. 1-8). (COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop). Association for Computational Linguistics (ACL).

Chiang, David ; Rambow, Owen. / The Hidden TAG Model : Synchronous Grammars for Parsing Resource-Poor Languages. COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2006. pp. 1-8 (COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop).

@inproceedings{e987edaa240341e8838039d52dcead5b,

title = "The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages",

abstract = "This paper discusses a novel probabilistic synchronous TAG formalism, synchronous Tree Substitution Grammar with sister adjunction (TSG+SA). We use it to parse a language for which there is no training data, by leveraging off a second, related language for which there is abundant training data. The grammar for the resource-rich side is automatically extracted from a treebank; the grammar on the resource-poor side and the synchronization are created by handwritten rules. Our approach thus represents a combination of grammar-based and empirical natural language processing. We discuss the approach using the example of Levantine Arabic and Standard Arabic. c2006 Association for Computational Linguistics.",

author = "David Chiang and Owen Rambow",

note = "Publisher Copyright: {\textcopyright} 2006 The Association for Computational Linguistics.; 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG 2006, co-located with COLING/ACL 2006 ; Conference date: 15-07-2006 Through 16-07-2006",

year = "2006",

language = "English",

series = "COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop",

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

pages = "1--8",

booktitle = "COLING/ACL 2006 - TAG+8",

}

Chiang, D & Rambow, O 2006, The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages. in COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop. COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 1-8, 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG 2006, co-located with COLING/ACL 2006, Sydney, Australia, 07/15/06.

The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages. / Chiang, David; Rambow, Owen.
COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2006. p. 1-8 (COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop).

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

TY - GEN

T1 - The Hidden TAG Model

T2 - 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG 2006, co-located with COLING/ACL 2006

AU - Chiang, David

AU - Rambow, Owen

PY - 2006

Y1 - 2006

N2 - This paper discusses a novel probabilistic synchronous TAG formalism, synchronous Tree Substitution Grammar with sister adjunction (TSG+SA). We use it to parse a language for which there is no training data, by leveraging off a second, related language for which there is abundant training data. The grammar for the resource-rich side is automatically extracted from a treebank; the grammar on the resource-poor side and the synchronization are created by handwritten rules. Our approach thus represents a combination of grammar-based and empirical natural language processing. We discuss the approach using the example of Levantine Arabic and Standard Arabic. c2006 Association for Computational Linguistics.

AB - This paper discusses a novel probabilistic synchronous TAG formalism, synchronous Tree Substitution Grammar with sister adjunction (TSG+SA). We use it to parse a language for which there is no training data, by leveraging off a second, related language for which there is abundant training data. The grammar for the resource-rich side is automatically extracted from a treebank; the grammar on the resource-poor side and the synchronization are created by handwritten rules. Our approach thus represents a combination of grammar-based and empirical natural language processing. We discuss the approach using the example of Levantine Arabic and Standard Arabic. c2006 Association for Computational Linguistics.

UR - https://www.scopus.com/pages/publications/84866842739

M3 - Conference contribution

T3 - COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop

SP - 1

EP - 8

BT - COLING/ACL 2006 - TAG+8

PB - Association for Computational Linguistics (ACL)

Y2 - 15 July 2006 through 16 July 2006

ER -

Chiang D, Rambow O. The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages. In COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2006. p. 1-8. (COLING/ACL 2006 - TAG+8: 8th International Workshop on Tree Adjoining Grammar and Related Formalisms, Proceedings of the Workshop).

The Hidden TAG Model: Synchronous Grammars for Parsing Resource-Poor Languages

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this