Word-order variation in natural language generation

Authors:
Aravind K. Joshi
Affiliations:
Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA
Venue:
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Year:
1987

Citing 3
Cited 0

Planning English Sentences

Planning English Sentences
Some computational properties of Tree Adjoining Grammars

ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
TAGs as a grammatical formalism for generation

ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In natural language generation the grammatical component has to be systematically interfaced to the other components of the system, for example, the planning component Grammatical formalisms can be studied with respect to their suitability for generation. The tree adjoining grammar (TAG) formalism has been previously studied in terms of incremental generation. In this paper, the TAG formalism has been investigated from the point of view of its ability to handle word-order variation in the context of generation. Word-order cannot be treated as a last minute adjustment of a structure; this position is not satisfactory cognitively or computationally. The grammatical framework has to be able to deal with the word-order phenomena in a way such that it can be systematically interfaced to the other components of the generation system.