Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
This work addresses the challenge of building multilingual NLP systems with limited annotated data, offering a scalable solution for zero-shot transfer across many languages, though it is incremental in combining existing techniques like BiLSTM and BPE.
The authors tackled the problem of learning multilingual sentence representations for 93 languages, enabling zero-shot cross-lingual transfer by training a classifier on English data and applying it to other languages without modification, achieving strong results on tasks like cross-lingual natural language inference and document classification.
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 BPE 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 dataset), cross-lingual document classification (MLDoc dataset) and parallel corpus mining (BUCC dataset) 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