Discovering Language-neutral Sub-networks in Multilingual Language Models
Negar Foroutan, Mohammadreza Banaei, Rémi Lebret, Antoine Bosselut, Karl Aberer
Abstract
Multilingual pre-trained language models transfer remarkably well on cross-lingual downstream tasks. However, the extent to which they learn language-neutral representations (i.e., shared representations that encode similar phenomena across languages), and the effect of such representations on cross-lingual transfer performance, remain open questions.In this work, we conceptualize language neutrality of multilingual models as a function of the overlap between language-encoding sub-networks of these models. We employ the lottery ticket hypothesis to discover sub-networks that are individually optimized for various languages and tasks. Our evaluation across three distinct tasks and eleven typologically-diverse languages demonstrates that sub-networks for different languages are topologically similar (i.e., language-neutral), making them effective initializations for cross-lingual transfer with limited performance degradation.- Anthology ID:
- 2022.emnlp-main.513
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7560–7575
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.513
- DOI:
- 10.18653/v1/2022.emnlp-main.513
- Cite (ACL):
- Negar Foroutan, Mohammadreza Banaei, Rémi Lebret, Antoine Bosselut, and Karl Aberer. 2022. Discovering Language-neutral Sub-networks in Multilingual Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7560–7575, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Discovering Language-neutral Sub-networks in Multilingual Language Models (Foroutan et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.513.pdf