A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition
This work addresses the problem of improving accuracy and flexibility in discourse analysis for NLP researchers, though it is incremental as it builds on existing frameworks like PDTB 3.0.
The paper tackles implicit discourse relation recognition by proposing a multi-task, multi-label classification model that jointly learns representations across sense levels, establishing the first benchmark for multi-label IDRR and achieving state-of-the-art results on single-label IDRR using DiscoGeM.
We propose a novel multi-label classification approach to implicit discourse relation recognition (IDRR). Our approach features a multi-task model that jointly learns multi-label representations of implicit discourse relations across all three sense levels in the PDTB 3.0 framework. The model can also be adapted to the traditional single-label IDRR setting by selecting the sense with the highest probability in the multi-label representation. We conduct extensive experiments to identify optimal model configurations and loss functions in both settings. Our approach establishes the first benchmark for multi-label IDRR and achieves SOTA results on single-label IDRR using DiscoGeM. Finally, we evaluate our model on the PDTB 3.0 corpus in the single-label setting, presenting the first analysis of transfer learning between the DiscoGeM and PDTB 3.0 corpora for IDRR.