Understanding Cross-Lingual Alignment—A Survey

MCML Authors

Katharina Hämmerl

→ Group Alexander Fraser
 Data Analytics & Statistics

Alexander Fraser

Prof. Dr.

Core PI

Data Analytics & Statistics

Abstract

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 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 decoder-only models, and argue that an effective trade-off between language-neutral and language-specific information is key.

inproceedings HLF24

---

Findings @ACL 2024

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand, Aug 11-16, 2024.

---

Authors

K. Hämmerl • J. Libovický • A. Fraser

---

Links

DOI

---

Research Area

 B2 | Natural Language Processing