Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation
This work addresses a challenging NLP problem for discourse analysis, offering an incremental improvement over existing methods.
The paper tackles implicit discourse relation classification by generating discourse connectives to address the absence of explicit markers, resulting in a model that significantly outperforms baselines on PDTB 2.0, PDTB 3.0, and PCC benchmarks.
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for the task, inspired by the annotation process of PDTB. Specifically, our model jointly learns to generate discourse connectives between arguments and predict discourse relations based on the arguments and the generated connectives. To prevent our relation classifier from being misled by poor connectives generated at the early stage of training while alleviating the discrepancy between training and inference, we adopt Scheduled Sampling to the joint learning. We evaluate our method on three benchmarks, PDTB 2.0, PDTB 3.0, and PCC. Results show that our joint model significantly outperforms various baselines on three datasets, demonstrating its superiority for the task.