Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning

David M. Howcroft, Dietrich Klakow, Vera Demberg


Abstract
Developing conventional natural language generation systems requires extensive attention from human experts in order to craft complex sets of sentence planning rules. We propose a Bayesian nonparametric approach to learn sentence planning rules by inducing synchronous tree substitution grammars for pairs of text plans and morphosyntactically-specified dependency trees. Our system is able to learn rules which can be used to generate novel texts after training on small datasets.
Anthology ID:
W18-6546
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Editors:
Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
391–396
Language:
URL:
https://aclanthology.org/W18-6546
DOI:
10.18653/v1/W18-6546
Bibkey:
Cite (ACL):
David M. Howcroft, Dietrich Klakow, and Vera Demberg. 2018. Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning. In Proceedings of the 11th International Conference on Natural Language Generation, pages 391–396, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning (Howcroft et al., INLG 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/W18-6546.pdf