Publication at Faculty of Mathematics and Physics |
2020
Abstract
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data.
We first produce a synthetic parallel corpus using unsupervised machine translation, and use it to fine-tune a pretrained cross-lingual masked language model (XLM) to derive the multilingual sentence representations. The quality of the representations is evaluated on two parallel corpus mining tasks with improvements of up to 22 F1 points over vanilla XLM.
In addition, we observe that a single synthetic bilingual corpus is able to improve results for other language pairs.