Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning
This addresses document-level translation challenges for NLP researchers and practitioners, offering an incremental improvement over existing in-context learning methods.
The paper tackles the problem of document-level machine translation using large language models with in-context learning, which often produces incoherent translations due to limited demonstration length, by proposing a Context-Aware Prompting method that improves translation accuracy and coherence, achieving strong results in zero pronoun and literary translation tasks.
Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major challenges: firstly, document translations generated by LLMs are often incoherent; secondly, the length of demonstration for in-context learning is usually limited. To address these issues, we propose a Context-Aware Prompting method (CAP), which enables LLMs to generate more accurate, cohesive, and coherent translations via in-context learning. CAP takes into account multi-level attention, selects the most relevant sentences to the current one as context, and then generates a summary from these collected sentences. Subsequently, sentences most similar to the summary are retrieved from the datastore as demonstrations, which effectively guide LLMs in generating cohesive and coherent translations. We conduct extensive experiments across various DOCMT tasks, and the results demonstrate the effectiveness of our approach, particularly in zero pronoun translation (ZPT) and literary translation tasks.