Reusing a statistical language model for generation

Authors:
Kevin Humphreys;Mike Calcagno;David Weise
Affiliations:
Natural Language Group, Microsoft Corporation, Redmond, WA;Natural Language Group, Microsoft Corporation, Redmond, WA;Natural Language Group, Microsoft Corporation, Redmond, WA
Venue:
EWNLG '01 Proceedings of the 8th European workshop on Natural Language Generation - Volume 8
Year:
2001

Citing 6
Cited 2

Semantic-head-driven generation

Computational Linguistics
Natural Language Processing: The Plnlp Approach

Natural Language Processing: The Plnlp Approach
Three generative, lexicalised models for statistical parsing

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Generation that exploits corpus-based statistical knowledge

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Two-level, many-paths generation

ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Exploiting a probabilistic hierarchical model for generation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1

Text generation from keywords

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

Natural Language Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

A relatively self-contained subtask of natural language generation is sentence realization: the process of generating a grammatically correct sentence from an abstract semantic / logical representation. We propose a method where sentence realization is carried out using a simplified (context free) version of a large analysis grammar, combined with a statistical language model from the full (context sensitive) version of the same grammar. The statistical model provides a measure of the probability of syntactic substructures, derived from the analysis of a corpus with the full grammar, and is used to guide both subsequent analysis and generation.