Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP
Publication Date
2018-07-10Journal Title
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)
Conference Name
56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)
ISBN
9781948087322
Publisher
Association for Computational Linguistics
Pages
1531-1542
Type
Conference Object
This Version
VoR
Metadata
Show full item recordCitation
Ponti, E., Reichart, R., Korhonen, A., & Vulic, I. (2018). Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), 1531-1542. https://doi.org/10.18653/v1/P18-1142
Abstract
The transfer or share of knowledge between languages is a popular solution to resource scarcity in NLP. However, the effectiveness of cross-lingual transfer can be challenged by variation in syntactic structures. Frameworks such as Universal Dependencies (UD) are designed to be cross-lingually consistent, but even in carefully designed resources trees representing equivalent sentences may not always overlap. In this paper, we measure cross-lingual syntactic variation, or anisomorphism, in the UD treebank collection, considering both morphological and structural properties. We show that reducing the level of anisomorphism yields consistent gains in cross-lingual transfer tasks. We introduce a source language selection procedure that facilitates effective cross-lingual parser transfer, and propose a typologically driven method for syntactic tree processing which reduces anisomorphism. Our results show the effectiveness of this method for both machine translation and cross-lingual sentence similarity, demonstrating the importance of syntactic structure compatibility for boosting cross-lingual transfer in NLP.
Sponsorship
European Research Council (648909)
Embargo Lift Date
2100-01-01
Identifiers
External DOI: https://doi.org/10.18653/v1/P18-1142
This record's URL: https://www.repository.cam.ac.uk/handle/1810/289394
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.