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

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 auxil...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-09
Main Authors: Artetxe, Mikel, Schwenk, Holger
Format: Article
Language:English
Subjects:
Data transfer (computers)
Languages
Multilingualism
Sentences
State of the art
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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
ISSN:2331-8422
DOI:10.48550/arxiv.1812.10464