Language-agnostic BERT Sentence Embedding

Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, Wei Wang


Abstract
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM), dual encoder translation ranking, and additive margin softmax. We show that introducing a pre-trained multilingual language model dramatically reduces the amount of parallel training data required to achieve good performance by 80%. Composing the best of these methods produces a model that achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, well above the 65.5% achieved by LASER, while still performing competitively on monolingual transfer learning benchmarks. Parallel data mined from CommonCrawl using our best model is shown to train competitive NMT models for en-zh and en-de. We publicly release our best multilingual sentence embedding model for 109+ languages at https://tfhub.dev/google/LaBSE.
Anthology ID:
2022.acl-long.62
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
878–891
Language:
URL:
https://aclanthology.org/2022.acl-long.62
DOI:
10.18653/v1/2022.acl-long.62
Bibkey:
Cite (ACL):
Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. Language-agnostic BERT Sentence Embedding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Language-agnostic BERT Sentence Embedding (Feng et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.62.pdf
Code
 additional community code
Data
MPQA Opinion CorpusSSTSentEval