Universal cross-lingual sentence embeddings map semantically similar
cross-lingual sentences into a shared embedding space. Aligning cross-lingual
sentence embeddings usually requires supervised cross-lingual parallel
sentences. In this work, we propose mSimCSE, which extends SimCSE to
multilingual settings and reveal that contrastive learning on English data can
surprisingly learn high-quality universal cross-lingual sentence embeddings
without any parallel data. In unsupervised and weakly supervised settings,
mSimCSE significantly improves previous sentence embedding methods on
cross-lingual retrieval and multilingual STS tasks. The performance of
unsupervised mSimCSE is comparable to fully supervised methods in retrieving
low-resource languages and multilingual STS. The performance can be further
enhanced when cross-lingual NLI data is available. Our code is publicly
available at this https URL.

本文提出了 mSimCSE，在英文数据上进行对比学习，不需要平行数据，可以学习高质量的通用跨语种句子嵌入。在无监督和弱监督设置中，mSimCSE 在跨语种检索和多语 STS 任务上显著改进了先前的句子嵌入方法。在检索低资源语言和多语 STS 任务上，无监督的 mSimCSE 表现与完全监督的方法相当。当跨语言 NLI 数据可用时，性能可以进一步提高。