Cross-lingual CCG Induction

Kilian Evang


Abstract
Combinatory categorial grammars are linguistically motivated and useful for semantic parsing, but costly to acquire in a supervised way and difficult to acquire in an unsupervised way. We propose an alternative making use of cross-lingual learning: an existing source-language parser is used together with a parallel corpus to induce a grammar and parsing model for a target language. On the PASCAL benchmark, cross-lingual CCG induction outperforms CCG induction from gold-standard POS tags on 3 out of 8 languages, and unsupervised CCG induction on 6 out of 8 languages. We also show that cross-lingually induced CCGs reflect syntactic properties of the target languages.
Anthology ID:
N19-1160
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1577–1587
Language:
URL:
https://aclanthology.org/N19-1160
DOI:
10.18653/v1/N19-1160
Bibkey:
Cite (ACL):
Kilian Evang. 2019. Cross-lingual CCG Induction. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1577–1587, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Cross-lingual CCG Induction (Evang, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1160.pdf
Presentation:
 N19-1160.Presentation.pdf
Video:
 https://vimeo.com/364705576
Code
 texttheater/xlci