Is bad structure better than no structure?: unsupervised parsing for realisation ranking

Yasaman Motazedi, Mark Dras, François Lareau

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

Abstract

In natural language generation using symbolic grammars, state-of-the-art realisation rankers use statistical models incorporating both language model and structural features. The rankers depend on multiple structures produced by the particular large-scale symbolic grammars to rank the output; for languages with smaller resources and in-development grammars, we look at the feasibility of an alternative source of structural features, unsupervised parsers. We show that, in spite of their lower quality of structure, raw sets of unsupervised parse features can be helpful with smaller language models; and that the parses do contain particular elements that can be highly useful, improving performance on our classification task by up to 10% on 60% of the test set leading to an overall improvement under a back-off model.

LanguageEnglish
Title of host publication24th International Conference on Computational Linguistics
Subtitle of host publicationProceedings of COLING 2012: Technical Papers
EditorsMartin Kay, Christian Boitet
Place of PublicationMumbai
PublisherIndian Institute of Technology
Pages1811-1830
Number of pages20
Publication statusPublished - 2012
Event24th International Conference on Computational Linguistics, COLING 2012 - Mumbai, India
Duration: 8 Dec 201215 Dec 2012

Other

Other24th International Conference on Computational Linguistics, COLING 2012
CountryIndia
CityMumbai
Period8/12/1215/12/12

Fingerprint

ranking
grammar
language
Parsing
Ranking
Grammar
resources
performance
Language Model
Language Generation
Parsers
Natural Language
Language
Resources
Statistical Model
Statistical Models

Cite this

Motazedi, Y., Dras, M., & Lareau, F. (2012). Is bad structure better than no structure? unsupervised parsing for realisation ranking. In M. Kay, & C. Boitet (Eds.), 24th International Conference on Computational Linguistics: Proceedings of COLING 2012: Technical Papers (pp. 1811-1830). Mumbai: Indian Institute of Technology.
Motazedi, Yasaman ; Dras, Mark ; Lareau, François. / Is bad structure better than no structure? unsupervised parsing for realisation ranking. 24th International Conference on Computational Linguistics: Proceedings of COLING 2012: Technical Papers. editor / Martin Kay ; Christian Boitet. Mumbai : Indian Institute of Technology, 2012. pp. 1811-1830
@inproceedings{4441c1fb19514af49c1fdb1459a72b88,
title = "Is bad structure better than no structure?: unsupervised parsing for realisation ranking",
abstract = "In natural language generation using symbolic grammars, state-of-the-art realisation rankers use statistical models incorporating both language model and structural features. The rankers depend on multiple structures produced by the particular large-scale symbolic grammars to rank the output; for languages with smaller resources and in-development grammars, we look at the feasibility of an alternative source of structural features, unsupervised parsers. We show that, in spite of their lower quality of structure, raw sets of unsupervised parse features can be helpful with smaller language models; and that the parses do contain particular elements that can be highly useful, improving performance on our classification task by up to 10{\%} on 60{\%} of the test set leading to an overall improvement under a back-off model.",
author = "Yasaman Motazedi and Mark Dras and Fran{\cc}ois Lareau",
year = "2012",
language = "English",
pages = "1811--1830",
editor = "Martin Kay and Christian Boitet",
booktitle = "24th International Conference on Computational Linguistics",
publisher = "Indian Institute of Technology",

}

Motazedi, Y, Dras, M & Lareau, F 2012, Is bad structure better than no structure? unsupervised parsing for realisation ranking. in M Kay & C Boitet (eds), 24th International Conference on Computational Linguistics: Proceedings of COLING 2012: Technical Papers. Indian Institute of Technology, Mumbai, pp. 1811-1830, 24th International Conference on Computational Linguistics, COLING 2012, Mumbai, India, 8/12/12.

Is bad structure better than no structure? unsupervised parsing for realisation ranking. / Motazedi, Yasaman; Dras, Mark; Lareau, François.

24th International Conference on Computational Linguistics: Proceedings of COLING 2012: Technical Papers. ed. / Martin Kay; Christian Boitet. Mumbai : Indian Institute of Technology, 2012. p. 1811-1830.

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

TY - GEN

T1 - Is bad structure better than no structure?

T2 - unsupervised parsing for realisation ranking

AU - Motazedi, Yasaman

AU - Dras, Mark

AU - Lareau, François

PY - 2012

Y1 - 2012

N2 - In natural language generation using symbolic grammars, state-of-the-art realisation rankers use statistical models incorporating both language model and structural features. The rankers depend on multiple structures produced by the particular large-scale symbolic grammars to rank the output; for languages with smaller resources and in-development grammars, we look at the feasibility of an alternative source of structural features, unsupervised parsers. We show that, in spite of their lower quality of structure, raw sets of unsupervised parse features can be helpful with smaller language models; and that the parses do contain particular elements that can be highly useful, improving performance on our classification task by up to 10% on 60% of the test set leading to an overall improvement under a back-off model.

AB - In natural language generation using symbolic grammars, state-of-the-art realisation rankers use statistical models incorporating both language model and structural features. The rankers depend on multiple structures produced by the particular large-scale symbolic grammars to rank the output; for languages with smaller resources and in-development grammars, we look at the feasibility of an alternative source of structural features, unsupervised parsers. We show that, in spite of their lower quality of structure, raw sets of unsupervised parse features can be helpful with smaller language models; and that the parses do contain particular elements that can be highly useful, improving performance on our classification task by up to 10% on 60% of the test set leading to an overall improvement under a back-off model.

UR - http://www.scopus.com/inward/record.url?scp=84876789571&partnerID=8YFLogxK

M3 - Conference proceeding contribution

SP - 1811

EP - 1830

BT - 24th International Conference on Computational Linguistics

A2 - Kay, Martin

A2 - Boitet, Christian

PB - Indian Institute of Technology

CY - Mumbai

ER -

Motazedi Y, Dras M, Lareau F. Is bad structure better than no structure? unsupervised parsing for realisation ranking. In Kay M, Boitet C, editors, 24th International Conference on Computational Linguistics: Proceedings of COLING 2012: Technical Papers. Mumbai: Indian Institute of Technology. 2012. p. 1811-1830