Abstract
Multilingual transfer learning can benefit both high- and low-resource languages, but the source of these improvements is not well understood. Cananical Correlation Analysis (CCA) of the internal representations of a pre- trained, multilingual BERT model reveals that the model partitions representations for each language rather than using a common, shared, interlingual space. This effect is magnified at deeper layers, suggesting that the model does not progressively abstract semantic con- tent while disregarding languages. Hierarchical clustering based on the CCA similarity scores between languages reveals a tree structure that mirrors the phylogenetic trees hand- designed by linguists. The subword tokenization employed by BERT provides a stronger bias towards such structure than character- and word-level tokenizations. We release a subset of the XNLI dataset translated into an additional 14 languages at https://www.github.com/salesforce/xnli_extension to assist further research into multilingual representations.- Anthology ID:
- D19-6106
- Volume:
- Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 47–55
- Language:
- URL:
- https://aclanthology.org/D19-6106
- DOI:
- 10.18653/v1/D19-6106
- Cite (ACL):
- Jasdeep Singh, Bryan McCann, Richard Socher, and Caiming Xiong. 2019. BERT is Not an Interlingua and the Bias of Tokenization. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 47–55, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- BERT is Not an Interlingua and the Bias of Tokenization (Singh et al., 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-6106.pdf
- Code
- salesforce/xnli_extension
- Data
- An Extension of XNLI