Neural sentence generation from formal semantics

Kana Manome, Masashi Yoshikawa, Hitomi Yanaka, Pascual Martínez-Gómez, Koji Mineshima, Daisuke Bekki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Sequence-to-sequence models have shown strong performance in a wide range of NLP tasks, yet their applications to sentence generation from logical representations are underdeveloped. In this paper, we present a sequence-to-sequence model for generating sentences from logical meaning representations based on event semantics. We use a semantic parsing system based on Combinatory Categorial Grammar (CCG) to obtain data annotated with logical formulas. We augment our sequence-to-sequence model with masking for predicates to constrain output sentences. We also propose a novel evaluation method for generation using Recognizing Textual Entailment (RTE). Combining parsing and generation, we test whether or not the output sentence entails the original text and vice versa. Experiments showed that our model outperformed a baseline with respect to both BLEU scores and accuracies in RTE.

Original languageEnglish
Title of host publicationINLG 2018 - 11th International Natural Language Generation Conference, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages408-414
Number of pages7
ISBN (Electronic)9781948087865
Publication statusPublished - 2018
Externally publishedYes
Event11th International Natural Language Generation Conference, INLG 2018 - Tilburg, Netherlands
Duration: 2018 Nov 52018 Nov 8

Publication series

NameINLG 2018 - 11th International Natural Language Generation Conference, Proceedings of the Conference

Conference

Conference11th International Natural Language Generation Conference, INLG 2018
Country/TerritoryNetherlands
CityTilburg
Period18/11/518/11/8

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Neural sentence generation from formal semantics'. Together they form a unique fingerprint.

Cite this