From OpenCCG to AI planning: Detecting infeasible edges in sentence generation

Maximilian Schwenger, Alvaro Torralba, Jörg Hoffmann, David M. Howcroft, Vera Demberg

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

2 Citations (Scopus)

Abstract

The search space in grammar-based natural language generation tasks can get very large, which is particularly problematic when generating long utterances or paragraphs. Using surface realization with OpenCCG as an example, we show that we can effectively detect partial solutions (edges) which cannot ultimately be part of a complete sentence because of their syntactic category. Formulating the completion of an edge into a sentence as finding a solution path in a large state-transition system, we demonstrate a connection to AI Planning which is concerned with this kind of problem. We design a compilation from OpenCCG into AI Planning allowing the detection of infeasible edges via AI Planning dead-end detection methods (proving the absence of a solution to the compilation). Our experiments show that this can filter out large fractions of infeasible edges in, and thus benefit the performance of, complex realization processes.

Original languageEnglish
Title of host publicationCOLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016
Number of pages11
PublisherAssociation for Computational Linguistics, ACL Anthology
Publication date2016
Pages1524-1534
ISBN (Print)9784879747020
Publication statusPublished - 2016
Externally publishedYes
Event26th International Conference on Computational Linguistics, COLING 2016 - Osaka, Japan
Duration: 11 Dec 201616 Dec 2016

Conference

Conference26th International Conference on Computational Linguistics, COLING 2016
Country/TerritoryJapan
CityOsaka
Period11/12/201616/12/2016
SeriesCOLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers

Keywords

  • Planning and scheduling

Fingerprint

Dive into the research topics of 'From OpenCCG to AI planning: Detecting infeasible edges in sentence generation'. Together they form a unique fingerprint.

Cite this