Cross-lingual Learning of an Open-domain Semantic Parser

Kilian Evang, Johan Bos


Abstract
We propose a method for learning semantic CCG parsers by projecting annotations via a parallel corpus. The method opens an avenue towards cheaply creating multilingual semantic parsers mapping open-domain text to formal meaning representations. A first cross-lingually learned Dutch (from English) semantic parser obtains f-scores ranging from 42.99% to 69.22% depending on the level of label informativity taken into account, compared to 58.40% to 78.88% for the underlying source-language system. These are promising numbers compared to state-of-the-art semantic parsing in open domains.
Anthology ID:
C16-1056
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
579–588
Language:
URL:
https://aclanthology.org/C16-1056
DOI:
Bibkey:
Cite (ACL):
Kilian Evang and Johan Bos. 2016. Cross-lingual Learning of an Open-domain Semantic Parser. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 579–588, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Cross-lingual Learning of an Open-domain Semantic Parser (Evang & Bos, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1056.pdf