Abstract
Multilingual language models exhibit better performance for some languages than for others (Singh et al., 2019), and many languages do not seem to benefit from multilingual sharing at all, presumably as a result of poor multilingual segmentation (Pyysal o et al., 2020). This work explores the idea of learning multilingual language models based on clustering of monolingual segments. We show significant improvements over standard multilingual segmentation and training across nine languages on a question answering task, both in a small model regime and for a model of the size of BERT-base.- Anthology ID:
- 2021.mrl-1.3
- Volume:
- Proceedings of the 1st Workshop on Multilingual Representation Learning
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- MRL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 32–40
- Language:
- URL:
- https://aclanthology.org/2021.mrl-1.3
- DOI:
- 10.18653/v1/2021.mrl-1.3
- Cite (ACL):
- Riccardo Bassani, Anders Søgaard, and Tejaswini Deoskar. 2021. Clustering Monolingual Vocabularies to Improve Cross-Lingual Generalization. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 32–40, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Clustering Monolingual Vocabularies to Improve Cross-Lingual Generalization (Bassani et al., MRL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.mrl-1.3.pdf
- Data
- TyDi QA