Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning
This work addresses a specific need for language learners by improving automated definition generation, though it is incremental as it builds on existing multilingual models.
The paper tackles the problem of generating definitions in a learner's native language rather than the target language, proposing a novel Trans-Lingual Definition Generation task. It introduces Prompt Combination and Contrastive Prompt Learning methods, showing superiority over baselines in generating higher-quality definitions across resource settings.
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.