In translation, a concept represented by a single word in a source language can have multiple variations in a target language. The task of lexical selection requires using context to identify which variation is most appropriate for a source text. We work with native speakers of nine languages to create DTAiLS, a dataset of 1,377 sentence pairs that exhibit cross-lingual concept variation when translating from English. We evaluate recent LLMs and neural machine translation systems on DTAiLS, with the best-performing model, GPT-4, achieving from 67 to 85% accuracy across languages. Finally, we use language models to generate English rules describing target-language concept variations. Providing weaker models with high-quality lexical rules improves accuracy substantially, in some cases reaching or outperforming GPT-4.

翻译：在翻译过程中，源语言中由单个词汇表达的概念在目标语言中可能存在多种对应变体。词汇选择任务需要借助上下文来确定哪种变体最适用于源文本。我们与九种语言的母语者合作构建了DTAiLS数据集，该数据集包含1,377个句对，展现了从英语翻译时出现的跨语言概念变异现象。我们在DTAiLS上评估了近期的大型语言模型和神经机器翻译系统，其中表现最佳的GPT-4模型在不同语言中取得了67%至85%的准确率。最后，我们利用语言模型生成描述目标语言概念变异的英语规则。为性能较弱的模型提供高质量的词汇规则可显著提升其准确率，在某些情况下甚至达到或超越了GPT-4的水平。