Semantic parsing with fuzzy meaning representations

Pavlo Kapustin, Michael Kapustin


Abstract
We propose an approach and a software framework for semantic parsing of natural language sentences to discourse representation structures with use of fuzzy meaning representations such as fuzzy sets and compatibility intervals. We explain the motivation for using fuzzy meaning representations in semantic parsing and describe the design of the proposed approach and the software framework, discussing various examples. We argue that the use of fuzzy meaning representations have potential to improve understanding and reasoning capabilities of systems working with natural language.
Anthology ID:
2020.dmr-1.8
Volume:
Proceedings of the Second International Workshop on Designing Meaning Representations
Month:
December
Year:
2020
Address:
Barcelona Spain (online)
Venues:
COLING | DMR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–89
Language:
URL:
https://www.aclweb.org/anthology/2020.dmr-1.8
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.dmr-1.8.pdf