Word Translation Without Parallel Data

TL;DR

This paper presents an unsupervised method for building bilingual dictionaries by aligning monolingual word embeddings without parallel data, outperforming some supervised methods and working well across diverse language pairs.

Contribution

The authors introduce a novel unsupervised approach to create bilingual dictionaries without parallel corpora, extending applicability to distant and low-resource language pairs.

Findings

Outperforms supervised methods on certain language pairs

Works effectively for distant language pairs like English-Russian and English-Chinese

Demonstrates potential for unsupervised machine translation in low-resource settings

Abstract

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.