Understanding Cross-Lingual Alignment - A Survey

Cross-lingual alignment, the meaningful similarity of representations across languages in multilingual language models, has been an active field of research in recent years.We survey the literature of techniques to improve cross-lingual alignment, providing a taxonomy of methods and summarising insights from throughout the field.We present different understandings of cross-lingual alignment and their limitations.We provide a qualitative summary of results from a large number of surveyed papers.Finally, we discuss how these insights may be applied not only to encoder models, where this topic has been heavily studied, but also to encoder-decoder or even decoderonly models, and argue that an effective tradeoff between language-neutral and languagespecific information is key.alignment and cross-lingual transfer in multilingual transformers.