Generation of referring expressions: managing structural ambiguities

Authors:
Imtiaz Hussain Khan;Kees van Deemter;Graeme Ritchie
Affiliations:
University of Aberdeen, Aberdeen, U.K.;University of Aberdeen, Aberdeen, U.K.;University of Aberdeen, Aberdeen, U.K.
Venue:
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Year:
2008

Citing 7
Cited 3

Building natural language generation systems

Building natural language generation systems
Generating referring expressions: boolean extensions of the incremental algorithm

Computational Linguistics
Text Revision: A Model and Its Implementation

Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Generating minimal definite descriptions

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
On identifying sets

INLG '00 Proceedings of the first international conference on Natural language generation - Volume 14
Identifying Nocuous Ambiguities in Natural Language Requirements

RE '06 Proceedings of the 14th IEEE International Requirements Engineering Conference
Generating referring expressions in open domains

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics

A hearer-oriented evaluation of referring expression generation

ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Computational generation of referring expressions: A survey

Computational Linguistics
Investigation into human preference between common and unambiguous lexical substitutions

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Existing algorithms for the Generation of Referring Expressions tend to generate distinguishing descriptions at the semantic level, disregarding the ways in which surface issues can affect their quality. This paper considers how these algorithms should deal with surface ambiguity, focussing on structural ambiguity. We propose that not all ambiguity is worth avoiding, and suggest some ways forward that attempt to avoid unwanted interpretations. We sketch the design of an algorithm motivated by our experimental findings.