Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring

Aitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka, Eneko Agirre


Abstract
Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing the target language embeddings, and learning a new set of embeddings for the source language that are aligned with them. To that end, we use an extension of skip-gram that leverages translated context words as anchor points, and incorporates self-learning and iterative restarts to reduce the dependency on the initial dictionary. Our approach outperforms conventional mapping methods on bilingual lexicon induction, and obtains competitive results in the downstream XNLI task.
Anthology ID:
2021.acl-long.506
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6479–6489
Language:
URL:
https://aclanthology.org/2021.acl-long.506
DOI:
10.18653/v1/2021.acl-long.506
Bibkey:
Cite (ACL):
Aitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka, and Eneko Agirre. 2021. Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6479–6489, Online. Association for Computational Linguistics.
Cite (Informal):
Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring (Ormazabal et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.506.pdf
Video:
 https://aclanthology.org/2021.acl-long.506.mp4
Data
XNLI