Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations

TL;DR

This study investigates how lexical semantics influence cross-lingual transfer, revealing that lexical matching significantly impacts alignment quality more than script or word order differences.

Contribution

It introduces a systematic analysis of language properties affecting cross-lingual transfer, emphasizing the importance of lexical matching over other factors.

Findings

Lexical matching greatly influences alignment quality.

Script and word order have limited impact.

Manipulating English sentences reveals the importance of lexical semantics.

Abstract

While cross-linguistic model transfer is effective in many settings, there is still limited understanding of the conditions under which it works. In this paper, we focus on assessing the role of lexical semantics in cross-lingual transfer, as we compare its impact to that of other language properties. Examining each language property individually, we systematically analyze how differences between English and a target language influence the capacity to align the language with an English pretrained representation space. We do so by artificially manipulating the English sentences in ways that mimic specific characteristics of the target language, and reporting the effect of each manipulation on the quality of alignment with the representation space. We show that while properties such as the script or word order only have a limited impact on alignment quality, the degree of lexical matching between the two languages, which we define using a measure of translation entropy, greatly affects it.