Abstract
Cross-lingual text classification alleviates the need for manually labeled documents in a target language by leveraging labeled documents from other languages. Existing approaches for transferring supervision across languages require expensive cross-lingual resources, such as parallel corpora, while less expensive cross-lingual representation learning approaches train classifiers without target labeled documents. In this work, we propose a cross-lingual teacher-student method, CLTS, that generates “weak” supervision in the target language using minimal cross-lingual resources, in the form of a small number of word translations. Given a limited translation budget, CLTS extracts and transfers only the most important task-specific seed words across languages and initializes a teacher classifier based on the translated seed words. Then, CLTS iteratively trains a more powerful student that also exploits the context of the seed words in unlabeled target documents and outperforms the teacher. CLTS is simple and surprisingly effective in 18 diverse languages: by transferring just 20 seed words, even a bag-of-words logistic regression student outperforms state-of-the-art cross-lingual methods (e.g., based on multilingual BERT). Moreover, CLTS can accommodate any type of student classifier: leveraging a monolingual BERT student leads to further improvements and outperforms even more expensive approaches by up to 12% in accuracy. Finally, CLTS addresses emerging tasks in low-resource languages using just a small number of word translations.- Anthology ID:
- 2020.findings-emnlp.323
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3604–3622
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.323
- DOI:
- 10.18653/v1/2020.findings-emnlp.323
- Cite (ACL):
- Giannis Karamanolakis, Daniel Hsu, and Luis Gravano. 2020. Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3604–3622, Online. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher (Karamanolakis et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.323.pdf
- Code
- gkaramanolakis/clts
- Data
- MLDoc