The standard definition generation task requires to automatically produce mono-lingual definitions (e.g., English definitions for English words), but ignores that the generated definitions may also consist of unfamiliar words for language learners. In this work, we propose a novel task of Trans-Lingual Definition Generation (TLDG), which aims to generate definitions in another language, i.e., the native speaker's language. Initially, we explore the unsupervised manner of this task and build up a simple implementation of fine-tuning the multi-lingual machine translation model. Then, we develop two novel methods, Prompt Combination and Contrastive Prompt Learning, for further enhancing the quality of the generation. Our methods are evaluated against the baseline Pipeline method in both rich- and low-resource settings, and we empirically establish its superiority in generating higher-quality trans-lingual definitions.

翻译：标准定义生成任务要求自动生成单语定义（例如，为英语单词生成英语定义），但忽略了生成的定义中可能包含对语言学习者而言陌生的词汇。在这项工作中，我们提出了一项新任务——跨语言定义生成（Trans-Lingual Definition Generation, TLDG），旨在用另一种语言（即母语者的语言）生成定义。首先，我们探索了该任务的无监督方式，并构建了微调多语言机器翻译模型的简单实现。然后，我们开发了两种新方法——提示组合（Prompt Combination）和对比提示学习（Contrastive Prompt Learning），以进一步提升生成质量。我们在丰富资源和低资源两种设置下，将我们的方法与基线流水线方法（Pipeline）进行了评估，并通过实验证明了其在生成更高质量的跨语言定义方面的优越性。