Combining Static and Contextualised Multilingual Embeddings

Hämmerl, Katharina; Libovický, Jindřich and Fraser, Alexander (2022): Combining Static and Contextualised Multilingual Embeddings. 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, May 22-27, 2022. Muresan, Smaranda; Nakov, Preslav and Villavicencio, Aline (eds.) : In: Findings of the Association for Computational Linguistics: ACL 2022, Stroudsburg, PA: Association for Computing Machinery. pp. 2316-2329

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.

• Item Type: Conference or Workshop Item (Paper)
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science; 400 Language > 400 Language
• Place of Publication: Stroudsburg, PA
• Annotation: ISBN 978-1-955917-25-4
• Language: English