Hybrid Semantics for Goal-Directed Natural Language Generation

Connor Baumler, Soumya Ray


Abstract
We consider the problem of generating natural language given a communicative goal and a world description. We ask the question: is it possible to combine complementary meaning representations to scale a goal-directed NLG system without losing expressiveness? In particular, we consider using two meaning representations, one based on logical semantics and the other based on distributional semantics. We build upon an existing goal-directed generation system, S-STRUCT, which models sentence generation as planning in a Markov decision process. We develop a hybrid approach, which uses distributional semantics to quickly and imprecisely add the main elements of the sentence and then uses first-order logic based semantics to more slowly add the precise details. We find that our hybrid method allows S-STRUCT’s generation to scale significantly better in early phases of generation and that the hybrid can often generate sentences with the same quality as S-STRUCT in substantially less time. However, we also observe and give insight into cases where the imprecision in distributional semantics leads to generation that is not as good as using pure logical semantics.
Anthology ID:
2022.acl-long.136
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1936–1946
Language:
URL:
https://aclanthology.org/2022.acl-long.136
DOI:
10.18653/v1/2022.acl-long.136
Bibkey:
Cite (ACL):
Connor Baumler and Soumya Ray. 2022. Hybrid Semantics for Goal-Directed Natural Language Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1936–1946, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Hybrid Semantics for Goal-Directed Natural Language Generation (Baumler & Ray, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.136.pdf