Abstract
We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a joint manner. Using this tool, we study to what extent and how morphosyntactic features are reflected in the representations learned by multilingual pre-trained models. We conduct a large-scale empirical study of over 33 languages and 17 morphosyntactic categories. Our findings demonstrate variations in the encoding of morphosyntactic information across upper and lower layers, with category-specific differences influenced by language properties. Hierarchical clustering of the factorization outputs yields a tree structure that is related to phylogenetic trees manually crafted by linguists. Moreover, we find the factorization outputs exhibit strong associations with performance observed across different cross-lingual tasks. We release our code to facilitate future research.- Anthology ID:
- 2023.findings-emnlp.851
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12764–12783
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.851
- DOI:
- 10.18653/v1/2023.findings-emnlp.851
- Cite (ACL):
- Zheng Zhao, Yftah Ziser, Bonnie Webber, and Shay Cohen. 2023. A Joint Matrix Factorization Analysis of Multilingual Representations. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12764–12783, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- A Joint Matrix Factorization Analysis of Multilingual Representations (Zhao et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.851.pdf