Self-Augmented In-Context Learning for Unsupervised Word Translation

arXiv:2402.10024v1 Announce Type: cross
Abstract: Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of 'traditional' mapping-based approaches in the unsupervised scenario where no seed translation pairs are available, especially for lower-resource languages. To address this challenge with LLMs, we propose self-augmented in-context learning (SAIL) for unsupervised BLI: starting from a zero-shot prompt, SAIL iteratively induces a set of high-confidence …

abstract arxiv bilingual capabilities context cs.ai cs.cl cs.ir cs.lg few-shot in-context learning language language models languages large language large language models llms mapping match performance seed translation type unsupervised word work