Learning from Omission

Bill McDowell, Noah Goodman


Abstract
Pragmatic reasoning allows humans to go beyond the literal meaning when interpret- ing language in context. Previous work has shown that such reasoning can improve the performance of already-trained language understanding systems. Here, we explore whether pragmatic reasoning during training can improve the quality of learned meanings. Our experiments on reference game data show that end-to-end pragmatic training produces more accurate utterance interpretation models, especially when data is sparse and language is complex.
Anthology ID:
P19-1059
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
619–628
Language:
URL:
https://aclanthology.org/P19-1059
DOI:
10.18653/v1/P19-1059
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/P19-1059.pdf