Understanding Linearity of Cross-Lingual Word Embedding Mappings
This addresses a critical research gap in cross-lingual NLP for low-resource languages, offering insights that could inspire more effective representation learning strategies.
The paper tackled the problem of understanding when linear mappings in cross-lingual word embeddings are valid, by presenting a theoretical analysis that identifies analogy preservation as a necessary and sufficient condition for linearity, and provided empirical support using a dataset covering five analogy categories across twelve languages.
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.