Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation

Haoran Xu, Philipp Koehn


Abstract
Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results. However, cross-lingual embedding space mapping is usually studied in static word-level embeddings, where a space transformation is derived by aligning representations of translation pairs that are referred from dictionaries. We move further from this line and investigate a contextual embedding alignment approach which is sense-level and dictionary-free. To enhance the quality of the mapping, we also provide a deep view of properties of contextual embeddings, i.e., the anisotropy problem and its solution. Experiments on zero-shot dependency parsing through the concept-shared space built by our embedding transformation substantially outperform state-of-the-art methods using multilingual embeddings.
Anthology ID:
2021.adaptnlp-1.21
Volume:
Proceedings of the Second Workshop on Domain Adaptation for NLP
Month:
April
Year:
2021
Address:
Kyiv, Ukraine
Editors:
Eyal Ben-David, Shay Cohen, Ryan McDonald, Barbara Plank, Roi Reichart, Guy Rotman, Yftah Ziser
Venue:
AdaptNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
204–213
Language:
URL:
https://aclanthology.org/2021.adaptnlp-1.21
DOI:
Bibkey:
Cite (ACL):
Haoran Xu and Philipp Koehn. 2021. Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation. In Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 204–213, Kyiv, Ukraine. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation (Xu & Koehn, AdaptNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.adaptnlp-1.21.pdf
Code
 fe1ixxu/ZeroShot-CrossLing-Parsing