Abstract
Static and contextual multilingual embeddings have complementary strengths. Static embeddings, while less expressive than contextual language models, can be more straightforwardly aligned across multiple languages. We combine the strengths of static and contextual models to improve multilingual representations. We extract static embeddings for 40 languages from XLM-R, validate those embeddings with cross-lingual word retrieval, and then align them using VecMap. This results in high-quality, highly multilingual static embeddings. Then we apply a novel continued pre-training approach to XLM-R, leveraging the high quality alignment of our static embeddings to better align the representation space of XLM-R. We show positive results for multiple complex semantic tasks. We release the static embeddings and the continued pre-training code. Unlike most previous work, our continued pre-training approach does not require parallel text.- Anthology ID:
- 2022.findings-acl.182
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2316–2329
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.182
- DOI:
- 10.18653/v1/2022.findings-acl.182
- Cite (ACL):
- Katharina Hämmerl, Jindřich Libovický, and Alexander Fraser. 2022. Combining Static and Contextualised Multilingual Embeddings. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2316–2329, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Combining Static and Contextualised Multilingual Embeddings (Hämmerl et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2022.findings-acl.182.pdf
- Code
- kathyhaem/combining-static-contextual
- Data
- TyDiQA, XQuAD