Abstract
We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared byte-pair encoding vocabulary for all languages, which is coupled with an auxiliary decoder and trained on publicly available parallel corpora. This enables us to learn a classifier on top of the resulting embeddings using English annotated data only, and transfer it to any of the 93 languages without any modification. Our experiments in cross-lingual natural language inference (XNLI data set), cross-lingual document classification (MLDoc data set), and parallel corpus mining (BUCC data set) show the effectiveness of our approach. We also introduce a new test set of aligned sentences in 112 languages, and show that our sentence embeddings obtain strong results in multilingual similarity search even for low- resource languages. Our implementation, the pre-trained encoder, and the multilingual test set are available at https://github.com/facebookresearch/LASER.- Anthology ID:
- Q19-1038
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 7
- Month:
- Year:
- 2019
- Address:
- Cambridge, MA
- Editors:
- Lillian Lee, Mark Johnson, Brian Roark, Ani Nenkova
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 597–610
- Language:
- URL:
- https://aclanthology.org/Q19-1038
- DOI:
- 10.1162/tacl_a_00288
- Cite (ACL):
- Mikel Artetxe and Holger Schwenk. 2019. Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond. Transactions of the Association for Computational Linguistics, 7:597–610.
- Cite (Informal):
- Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond (Artetxe & Schwenk, TACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/Q19-1038.pdf
- Code
- facebookresearch/LASER + additional community code
- Data
- Tatoeba, BUCC, MLDoc, XNLI