Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition
This addresses a crucial problem in discourse analysis for NLP researchers, offering a novel approach to improve performance on fine-grained and few-shot implicit discourse relations, though it appears incremental by building on existing pre-trained models.
The authors tackled the challenge of fine-grained implicit discourse relation recognition (IDRR) by proposing a Prompt-based Connective Prediction (PCP) method that leverages large-scale pre-trained models and the correlation between connectives and discourse relations, achieving state-of-the-art results with significant improvements on fine-grained few-shot classes.
Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis. Most of the current work adopted multi-task learning to aid IDRR through explicit discourse relation recognition (EDRR) or utilized dependencies between discourse relation labels to constrain model predictions. But these methods still performed poorly on fine-grained IDRR and even utterly misidentified on most of the few-shot discourse relation classes. To address these problems, we propose a novel Prompt-based Connective Prediction (PCP) method for IDRR. Our method instructs large-scale pre-trained models to use knowledge relevant to discourse relation and utilizes the strong correlation between connectives and discourse relation to help the model recognize implicit discourse relations. Experimental results show that our method surpasses the current state-of-the-art model and achieves significant improvements on those fine-grained few-shot discourse relation. Moreover, our approach is able to be transferred to EDRR and obtain acceptable results. Our code is released in https://github.com/zh-i9/PCP-for-IDRR.