Enhanced semantic representation learning for implicit discourse relation classification

Implicit discourse relation classification is one of the most challenging tasks in discourse parsing. Without connectives as linguistic clues, classifying discourse relations usually requires understanding text semantics at the word level, sentence level, and sentence span level. In this paper, we mainly proposed a graph-based model for relation classification. A semantic graph is firstly built to describe the syntactic dependencies and sentence interaction. Then, based on the learning principle of graph neural networks, a bidirectional gated recurrent unit (Bi-GRU) was introduced to work with graph attention network (GAT), which allows the expanded GAT to capture syntactic dependencies of long-distance nodes and selectively mine semantic features from multi-hop neighborhood nodes. In addition, we utilized the hierarchical self-organization ability of hyperbolic spaces to classify multi-level discourse relations, improving the accuracy of fine-grained discourse relation classification. Experimental results on Penn Discourse Treebank 2.0 (PDTB 2.0) demonstrated that our model could achieve improvements without any external knowledge.