An Unsupervised Approach for Mapping between Vector Spaces

TL;DR

This paper introduces an unsupervised, language-independent method for mapping word embeddings across languages using a transformation matrix, improving cross-lingual word similarity and analogy tasks without requiring labeled data.

Contribution

The paper presents a novel unsupervised approach for cross-lingual embedding mapping that handles data scarcity and improves over state-of-the-art results across multiple language pairs.

Findings

13% improvement for French word similarity

19% improvement for German word similarity

16% increase for Urdu word similarity

Abstract

We present a language independent, unsupervised approach for transforming word embeddings from source language to target language using a transformation matrix. Our model handles the problem of data scarcity which is faced by many languages in the world and yields improved word embeddings for words in the target language by relying on transformed embeddings of words of the source language. We initially evaluate our approach via word similarity tasks on a similar language pair - Hindi as source and Urdu as the target language, while we also evaluate our method on French and German as target languages and English as source language. Our approach improves the current state of the art results - by 13% for French and 19% for German. For Urdu, we saw an increment of 16% over our initial baseline score. We further explore the prospects of our approach by applying it on multiple models of the same language and transferring words between the two models, thus solving the problem of missing words in a model. We evaluate this on word similarity and word analogy tasks.