An incremental algorithm for transition-based CCG parsing

Bharat Ram Ambati, Tejaswini Deoskar, Mark Johnson, Mark Steedman

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of 'revealing' (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88% in labeled and 2.0% in unlabeled F-score over a greedy non-incremental shift-reduce parser.

LanguageEnglish
Title of host publication2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015
Subtitle of host publicationHuman Language Technologies, Proceedings of the Conference
Place of PublicationRed Hook, NY
PublisherAssociation for Computational Linguistics (ACL)
Pages53-63
Number of pages11
ISBN (Electronic)9781941643495
Publication statusPublished - 2015
EventConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States
Duration: 31 May 20155 Jun 2015

Other

OtherConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
CountryUnited States
CityDenver
Period31/05/155/06/15

Fingerprint

Speech recognition
grammar
paradigm
language
Parsing
Speech Recognition
Categorial Grammar
Parsers
Paradigm Shift
Language Modeling
Machine Translation

Cite this

Ambati, B. R., Deoskar, T., Johnson, M., & Steedman, M. (2015). An incremental algorithm for transition-based CCG parsing. In 2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015: Human Language Technologies, Proceedings of the Conference (pp. 53-63). Red Hook, NY: Association for Computational Linguistics (ACL).
Ambati, Bharat Ram ; Deoskar, Tejaswini ; Johnson, Mark ; Steedman, Mark. / An incremental algorithm for transition-based CCG parsing. 2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015: Human Language Technologies, Proceedings of the Conference. Red Hook, NY : Association for Computational Linguistics (ACL), 2015. pp. 53-63
@inproceedings{7362f6247d9242929a3c6fac7006ef71,
title = "An incremental algorithm for transition-based CCG parsing",
abstract = "Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of 'revealing' (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88{\%} in labeled and 2.0{\%} in unlabeled F-score over a greedy non-incremental shift-reduce parser.",
author = "Ambati, {Bharat Ram} and Tejaswini Deoskar and Mark Johnson and Mark Steedman",
year = "2015",
language = "English",
pages = "53--63",
booktitle = "2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015",
publisher = "Association for Computational Linguistics (ACL)",

}

Ambati, BR, Deoskar, T, Johnson, M & Steedman, M 2015, An incremental algorithm for transition-based CCG parsing. in 2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), Red Hook, NY, pp. 53-63, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, Denver, United States, 31/05/15.

An incremental algorithm for transition-based CCG parsing. / Ambati, Bharat Ram; Deoskar, Tejaswini; Johnson, Mark; Steedman, Mark.

2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015: Human Language Technologies, Proceedings of the Conference. Red Hook, NY : Association for Computational Linguistics (ACL), 2015. p. 53-63.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - An incremental algorithm for transition-based CCG parsing

AU - Ambati, Bharat Ram

AU - Deoskar, Tejaswini

AU - Johnson, Mark

AU - Steedman, Mark

PY - 2015

Y1 - 2015

N2 - Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of 'revealing' (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88% in labeled and 2.0% in unlabeled F-score over a greedy non-incremental shift-reduce parser.

AB - Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of 'revealing' (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88% in labeled and 2.0% in unlabeled F-score over a greedy non-incremental shift-reduce parser.

UR - http://www.scopus.com/inward/record.url?scp=84960088489&partnerID=8YFLogxK

M3 - Conference proceeding contribution

SP - 53

EP - 63

BT - 2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015

PB - Association for Computational Linguistics (ACL)

CY - Red Hook, NY

ER -

Ambati BR, Deoskar T, Johnson M, Steedman M. An incremental algorithm for transition-based CCG parsing. In 2015 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2015: Human Language Technologies, Proceedings of the Conference. Red Hook, NY: Association for Computational Linguistics (ACL). 2015. p. 53-63