A Wide-Coverage Symbolic Natural Language Inference System

Stergios Chatzikyriakidis, Jean-Philippe Bernardy


Abstract
We present a system for Natural Language Inference which uses a dynamic semantics converter from abstract syntax trees to Coq types. It combines the fine-grainedness of a dynamic semantics system with the powerfulness of a state-of-the-art proof assistant, like Coq. We evaluate the system on all sections of the FraCaS test suite, excluding section 6. This is the first system that does a complete run on the anaphora and ellipsis sections of the FraCaS. It has a better overall accuracy than any previous system.
Anthology ID:
W19-6131
Volume:
Proceedings of the 22nd Nordic Conference on Computational Linguistics
Month:
September–October
Year:
2019
Address:
Turku, Finland
Editors:
Mareike Hartmann, Barbara Plank
Venue:
NoDaLiDa
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
298–303
Language:
URL:
https://aclanthology.org/W19-6131
DOI:
Bibkey:
Cite (ACL):
Stergios Chatzikyriakidis and Jean-Philippe Bernardy. 2019. A Wide-Coverage Symbolic Natural Language Inference System. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 298–303, Turku, Finland. Linköping University Electronic Press.
Cite (Informal):
A Wide-Coverage Symbolic Natural Language Inference System (Chatzikyriakidis & Bernardy, NoDaLiDa 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/W19-6131.pdf