Leveraging Hierarchical Prototypes as the Verbalizer for Implicit Discourse Relation Recognition
This work addresses the challenge of implicit discourse relation recognition in NLP, offering a more versatile and practical solution for cross-lingual applications, though it is incremental as it builds on the pre-train, prompt, and predict paradigm.
The paper tackles the problem of implicit discourse relation recognition by introducing hierarchical prototypes as verbalizers to address ambiguity and incorrectness in manual verbalizers, resulting in improved performance over competitive baselines and enabling zero-shot cross-lingual learning for languages with scarce resources.
Implicit discourse relation recognition involves determining relationships that hold between spans of text that are not linked by an explicit discourse connective. In recent years, the pre-train, prompt, and predict paradigm has emerged as a promising approach for tackling this task. However, previous work solely relied on manual verbalizers for implicit discourse relation recognition, which suffer from issues of ambiguity and even incorrectness. To overcome these limitations, we leverage the prototypes that capture certain class-level semantic features and the hierarchical label structure for different classes as the verbalizer. We show that our method improves on competitive baselines. Besides, our proposed approach can be extended to enable zero-shot cross-lingual learning, facilitating the recognition of discourse relations in languages with scarce resources. These advancement validate the practicality and versatility of our approach in addressing the issues of implicit discourse relation recognition across different languages.