Multilingual Grammar Induction with Continuous Language Identification

Wenjuan Han, Ge Wang, Yong Jiang, Kewei Tu


Abstract
The key to multilingual grammar induction is to couple grammar parameters of different languages together by exploiting the similarity between languages. Previous work relies on linguistic phylogenetic knowledge to specify similarity between languages. In this work, we propose a novel universal grammar induction approach that represents language identities with continuous vectors and employs a neural network to predict grammar parameters based on the representation. Without any prior linguistic phylogenetic knowledge, we automatically capture similarity between languages with the vector representations and softly tie the grammar parameters of different languages. In our experiments, we apply our approach to 15 languages across 8 language families and subfamilies in the Universal Dependency Treebank dataset, and we observe substantial performance gain on average over monolingual and multilingual baselines.
Anthology ID:
D19-1576
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5728–5733
Language:
URL:
https://aclanthology.org/D19-1576
DOI:
10.18653/v1/D19-1576
Bibkey:
Cite (ACL):
Wenjuan Han, Ge Wang, Yong Jiang, and Kewei Tu. 2019. Multilingual Grammar Induction with Continuous Language Identification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5728–5733, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Multilingual Grammar Induction with Continuous Language Identification (Han et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1576.pdf