Skip to main content

Research Repository

Advanced Search

Inducing Clause-Combining Rules: A Case Study with the SPaRKy Restaurant Corpus

White, Michael; Howcroft, David M.

Authors

Michael White



Abstract

We describe an algorithm for inducing clause-combining rules for use in a traditional natural language generation architecture. An experiment pairing lexicalized text plans from the SPaRKy Restaurant Corpus with logical forms obtained by parsing the corresponding sentences demonstrates that the approach is able to learn clause-combining operations which have essentially the same coverage as those used in the SPaRKy Restaurant Corpus. This paper fills a gap in the literature, showing that it is possible to learn microplanning rules for both aggregation and discourse connective insertion, an important step towards ameliorating the knowledge acquisition bottleneck for NLG systems that produce texts with rich discourse structures using traditional architectures.

Citation

White, M., & Howcroft, D. M. (2015). Inducing Clause-Combining Rules: A Case Study with the SPaRKy Restaurant Corpus. In Proceedings of the 15th European Workshop on Natural Language Generation (ENLG) (28-37). https://doi.org/10.18653/v1/w15-4704

Conference Name 15th European Workshop on Natural Language Generation (ENLG)
Conference Location Brighton, UK
Start Date Sep 10, 2015
End Date Sep 11, 2015
Publication Date 2015
Deposit Date Aug 25, 2021
Publicly Available Date Aug 25, 2021
Publisher Association for Computational Linguistics (ACL)
Pages 28-37
Book Title Proceedings of the 15th European Workshop on Natural Language Generation (ENLG)
DOI https://doi.org/10.18653/v1/w15-4704
Public URL http://researchrepository.napier.ac.uk/Output/2794503
Publisher URL https://aclanthology.org/W15-4704/

Files

Inducing Clause-Combining Rules: A Case Study With The SPaRKy Restaurant Corpus (<nobr>147 Kb</nobr>)
PDF

Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/

Copyright Statement
Published under a Creative Commons Attribution 4.0 International License: https://creativecommons.org/licenses/by/4.0/





You might also like



Downloadable Citations