A Stacking Gated Neural Architecture for Implicit Discourse Relation Classification

Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in which a convolutional neural network (CNN) is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation. Our evaluation and comparisons show that the proposed model outperforms previous state-of-the-art systems.