Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
This work addresses the problem of optimizing cross-lingual transfer for linguistically distant languages, which is incremental as it builds on prior research on linguistic features.
The study investigated how linguistic distance affects cross-lingual transfer by analyzing representation spaces in multilingual language models, finding preliminary evidence that this can improve transfer to distant languages.
Prior research has investigated the impact of various linguistic features on cross-lingual transfer performance. In this study, we investigate the manner in which this effect can be mapped onto the representation space. While past studies have focused on the impact on cross-lingual alignment in multilingual language models during fine-tuning, this study examines the absolute evolution of the respective language representation spaces produced by MLLMs. We place a specific emphasis on the role of linguistic characteristics and investigate their inter-correlation with the impact on representation spaces and cross-lingual transfer performance. Additionally, this paper provides preliminary evidence of how these findings can be leveraged to enhance transfer to linguistically distant languages.