Corpus-based lexical choice in natural language generation

Srinivas Bangalore; Owen Rambow

Corpus-based lexical choice in natural language generation

Srinivas Bangalore
, Owen Rambow

Linguistics

AT&T

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

35 Scopus citations

Abstract

Choosing the best lexeme to realize a meaning in natural language generation is a hard task. We investigate different tree-based stochastic models for lexical choice. Because of the difficulty of obtaining a sense-tagged corpus, we generalize the notion of synonymy. We show that a tree-based model can achieve a word-bag based accuracy of 90%, representing an improvement over the baseline.

Original language	English
Journal	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2000-October
State	Published - 2000
Event	38th Annual Meeting of the Association for Computational Linguistics, ACL 2000 - Hong Kong, China Duration: Oct 1 2000 → Oct 8 2000

Cite this

@article{a22a76941be543b39573507773a28597,

title = "Corpus-based lexical choice in natural language generation",

abstract = "Choosing the best lexeme to realize a meaning in natural language generation is a hard task. We investigate different tree-based stochastic models for lexical choice. Because of the difficulty of obtaining a sense-tagged corpus, we generalize the notion of synonymy. We show that a tree-based model can achieve a word-bag based accuracy of 90\%, representing an improvement over the baseline.",

author = "Srinivas Bangalore and Owen Rambow",

note = "Publisher Copyright: {\textcopyright} 2000 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All Rights Reserved.; 38th Annual Meeting of the Association for Computational Linguistics, ACL 2000 ; Conference date: 01-10-2000 Through 08-10-2000",

year = "2000",

language = "English",

volume = "2000-October",

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

issn = "0736-587X",

}

TY - JOUR

T1 - Corpus-based lexical choice in natural language generation

AU - Bangalore, Srinivas

AU - Rambow, Owen

PY - 2000

Y1 - 2000

N2 - Choosing the best lexeme to realize a meaning in natural language generation is a hard task. We investigate different tree-based stochastic models for lexical choice. Because of the difficulty of obtaining a sense-tagged corpus, we generalize the notion of synonymy. We show that a tree-based model can achieve a word-bag based accuracy of 90%, representing an improvement over the baseline.

AB - Choosing the best lexeme to realize a meaning in natural language generation is a hard task. We investigate different tree-based stochastic models for lexical choice. Because of the difficulty of obtaining a sense-tagged corpus, we generalize the notion of synonymy. We show that a tree-based model can achieve a word-bag based accuracy of 90%, representing an improvement over the baseline.

UR - https://www.scopus.com/pages/publications/85149104154

M3 - Conference article

AN - SCOPUS:85149104154

SN - 0736-587X

VL - 2000-October

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 - 38th Annual Meeting of the Association for Computational Linguistics, ACL 2000

Y2 - 1 October 2000 through 8 October 2000

ER -

Corpus-based lexical choice in natural language generation

Abstract

Other files and links

Fingerprint

Cite this