A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the performance from training on English tasks to non-English tasks, despite little to no task-specific non-English data. In this paper, we explore a natural setup for learning cross-lingual sentence representations: the dual-encoder. We provide a comprehensive evaluation of our cross-lingual representations on a number of monolingual, cross-lingual, and zero-shot/few-shot learning tasks, and also give an analysis of different learned cross-lingual embedding spaces.
@article{arxiv.1810.12836,
title = {Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model},
author = {Muthuraman Chidambaram and Yinfei Yang and Daniel Cer and Steve Yuan and Yun-Hsuan Sung and Brian Strope and Ray Kurzweil},
journal= {arXiv preprint arXiv:1810.12836},
year = {2019}
}
Comments
Accepted at the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)