Corpus-based lexical choice in natural language generation

Authors:
Srinivas Bangalore;Owen Rambow
Affiliations:
AT&T Labs --- Research, Florham Park, NJ;AT&T Labs --- Research, Florham Park, NJ
Venue:
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Year:
2000

Citing 5
Cited 11

Machine translation divergences: a formal description and proposed solution

Computational Linguistics
Supertagging: an approach to almost parsing

Computational Linguistics
Generation that exploits corpus-based statistical knowledge

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Exploiting a probabilistic hierarchical model for generation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Evaluation metrics for generation

INLG '00 Proceedings of the first international conference on Natural language generation - Volume 14

Hybrid Natural Language Generation from Lexical Conceptual Structures

Machine Translation
Natural language generation in dialog systems

HLT '01 Proceedings of the first international conference on Human language technology research
Mapping lexical entries in a verbs database to WordNet senses

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Machine Translation
Instance-based natural language generation

Natural Language Engineering
Text generation for Brazilian Portuguese: the surface realization task

YIWCALA '10 Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas
Improved text generation using n-gram statistics

IBERAMIA'10 Proceedings of the 12th Ibero-American conference on Advances in artificial intelligence
Text-to-text surface realisation using dependency-tree replacement

IBERAMIA'10 Proceedings of the 12th Ibero-American conference on Advances in artificial intelligence
Generating phrasal and sentential paraphrases: A survey of data-driven methods

Computational Linguistics
Highly-inflected language generation using factored language models

CICLing'11 Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part I
Assessing the influence of personal preferences on the choice of vocabulary for natural language generation

Information Processing and Management: an International Journal

Quantified Score

Hi-index	0.00

Visualization

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.