Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models
This is an incremental survey paper that synthesizes existing research on context-aware machine translation with LLMs for researchers and practitioners in natural language processing.
This survey examines the underexplored application of large language models (LLMs) to context-aware machine translation, finding that commercial LLMs like ChatGPT outperform open-source models and prompt-based approaches provide effective baselines for translation quality assessment.
Despite the popularity of the large language models (LLMs), their application to machine translation is relatively underexplored, especially in context-aware settings. This work presents a literature review of context-aware translation with LLMs. The existing works utilise prompting and fine-tuning approaches, with few focusing on automatic post-editing and creating translation agents for context-aware machine translation. We observed that the commercial LLMs (such as ChatGPT and Tower LLM) achieved better results than the open-source LLMs (such as Llama and Bloom LLMs), and prompt-based approaches serve as good baselines to assess the quality of translations. Finally, we present some interesting future directions to explore.