Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

Citations Over TimeTop 10% of 2019 papers

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 .

Related Papers

• → (2019)31,543 cited
• → Attention Is All You Need(2025)6,509 cited
• → Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation(2017)1,724 cited
• → Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond(2018)753 cited
• → Cross-lingual Language Model Pretraining(2019)1,617 cited