Abstract
Multilingual contextual embeddings, such as multilingual BERT and XLM-RoBERTa, have proved useful for many multi-lingual tasks. Previous work probed the cross-linguality of the representations indirectly using zero-shot transfer learning on morphological and syntactic tasks. We instead investigate the language-neutrality of multilingual contextual embeddings directly and with respect to lexical semantics. Our results show that contextual embeddings are more language-neutral and, in general, more informative than aligned static word-type embeddings, which are explicitly trained for language neutrality. Contextual embeddings are still only moderately language-neutral by default, so we propose two simple methods for achieving stronger language neutrality: first, by unsupervised centering of the representation for each language and second, by fitting an explicit projection on small parallel data. Besides, we show how to reach state-of-the-art accuracy on language identification and match the performance of statistical methods for word alignment of parallel sentences without using parallel data.- Anthology ID:
- 2020.findings-emnlp.150
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1663–1674
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.150
- DOI:
- 10.18653/v1/2020.findings-emnlp.150
- Cite (ACL):
- Jindřich Libovický, Rudolf Rosa, and Alexander Fraser. 2020. On the Language Neutrality of Pre-trained Multilingual Representations. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1663–1674, Online. Association for Computational Linguistics.
- Cite (Informal):
- On the Language Neutrality of Pre-trained Multilingual Representations (Libovický et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.findings-emnlp.150.pdf
- Code
- jlibovicky/assess-multilingual-bert
- Data
- WMT 2014, XNLI