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.

翻译：隐式篇章关系分类因缺乏话语连接词而成为一项具有挑战性的任务。为解决该问题，受PDTB标注过程的启发，我们设计了一种端到端神经模型，显式地生成话语连接词以辅助分类。具体而言，该模型联合学习生成论证间的话语连接词，并基于论证及所生成的连接词预测篇章关系。为避免早期训练阶段生成的劣质连接词误导关系分类器，同时缓解训练与推理之间的差异，我们在联合学习中引入调度采样策略。我们在PDTB 2.0、PDTB 3.0和PCC三个基准数据集上评估了该方法。结果表明，我们的联合模型在三个数据集上均显著优于多种基线模型，证明了其在任务中的优越性。