通过逐步翻译桥接句，提升大模型低资源语言翻译能力。
BridG MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Bridging and Gradual MT
- 用中间句构建从易到难的翻译桥梁
- 在7种语言上超越大量示例的翻译方法
- 适合低资源语言翻译场景的模型优化
近期的大语言模型（LLMs）在无需额外平行语料微调的情况下已展现出出色的翻译性能。然而，在低资源语言场景下仍面临显著挑战。常见做法是提供少量示例作为外部知识辅助翻译，但受限于示例的质量或数量，难以保证效果。为减少对这类外部依赖，本文提出BridG MT：结合句子桥接（Sentence Bridging）与渐进式翻译（Gradual MT）。Sentence Bridging生成一系列从易到难的过渡句，Gradual MT则逐句翻译，并将前序结果作为后续翻译的少样本示例。在四个LLMs和七种语言上的实验表明，该方法显著提升翻译性能，甚至优于依赖大量示例的翻译方法。
原文摘要 · Abstract (English)
Recent Large Language Models (LLMs) have demonstrated impressive translation performance without requiring fine-tuning on additional parallel corpora. However, they still face significant challenges in certain scenarios, particularly when translating low-resource languages. A common approach to address this issue is to provide external knowledge, such as few-shot examples, to assist LLMs in translating specific source sentences. However, this method is fundamentally limited by the quality or quantity of relevant sources, which cannot always be guaranteed. To reduce LLMs' reliance on external sources, we propose BridG MT, a method that combines Sentence Bridging, which generates a sequence of sentences as a bridge that gradually transition from easy-to-translate to more difficult, and Gradual MT, which sequentially translates these sentences using earlier translations as few-shot examples for subsequent ones. Experiments conducted on four LLMs across seven languages demonstrate that our method effectively enhances translation performance, even outperforming translation methods that rely on a large number of few-shot examples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。