Understanding Linearity of Cross-Lingual Word Embedding Mappings

TL;DR

This paper provides a theoretical analysis showing that the linearity of cross-lingual word embedding mappings depends on the preservation of monolingual analogies, supported by experiments across multiple languages.

Contribution

It is the first to theoretically link analogy preservation to the linearity of CLWE mappings and empirically validate this relationship across diverse languages.

Findings

Linearity of CLWE mappings is necessary and sufficient for analogy preservation.

Empirical support from experiments on 12 languages and 5 analogy categories.

Insights into when linear mappings are appropriate for cross-lingual embeddings.

Abstract

The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages. Its dominant approaches assumed that the relationship between embeddings could be represented by a linear mapping, but there has been no exploration of the conditions under which this assumption holds. Such a research gap becomes very critical recently, as it has been evidenced that relaxing mappings to be non-linear can lead to better performance in some cases. We, for the first time, present a theoretical analysis that identifies the preservation of analogies encoded in monolingual word embeddings as a necessary and sufficient condition for the ground-truth CLWE mapping between those embeddings to be linear. On a novel cross-lingual analogy dataset that covers five representative analogy categories for twelve distinct languages, we carry out experiments which provide direct empirical support for our theoretical claim. These results offer additional insight into the observations of other researchers and contribute inspiration for the development of more effective cross-lingual representation learning strategies.