Interactive Refinement of Cross-Lingual Word Embeddings

Michelle Yuan, Mozhi Zhang, Benjamin Van Durme, Leah Findlater, Jordan Boyd-Graber


Abstract
Cross-lingual word embeddings transfer knowledge between languages: models trained on high-resource languages can predict in low-resource languages. We introduce CLIME, an interactive system to quickly refine cross-lingual word embeddings for a given classification problem. First, CLIME ranks words by their salience to the downstream task. Then, users mark similarity between keywords and their nearest neighbors in the embedding space. Finally, CLIME updates the embeddings using the annotations. We evaluate CLIME on identifying health-related text in four low-resource languages: Ilocano, Sinhalese, Tigrinya, and Uyghur. Embeddings refined by CLIME capture more nuanced word semantics and have higher test accuracy than the original embeddings. CLIME often improves accuracy faster than an active learning baseline and can be easily combined with active learning to improve results.
Anthology ID:
2020.emnlp-main.482
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5984–5996
Language:
URL:
https://aclanthology.org/2020.emnlp-main.482
DOI:
10.18653/v1/2020.emnlp-main.482
Bibkey:
Cite (ACL):
Michelle Yuan, Mozhi Zhang, Benjamin Van Durme, Leah Findlater, and Jordan Boyd-Graber. 2020. Interactive Refinement of Cross-Lingual Word Embeddings. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5984–5996, Online. Association for Computational Linguistics.
Cite (Informal):
Interactive Refinement of Cross-Lingual Word Embeddings (Yuan et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.482.pdf
Video:
 https://slideslive.com/38938732
Code
 forest-snow/clime-ui