Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
This work addresses a challenging NLP task for discourse analysis researchers, but appears incremental as it builds on existing tree-structured neural networks.
The authors tackled implicit discourse relation classification by incorporating syntactic parse trees and constituent tags into Tree-LSTM and Tree-GRU models, achieving state-of-the-art performance on the PDTB corpus.
Identifying implicit discourse relations between text spans is a challenging task because it requires understanding the meaning of the text. To tackle this task, recent studies have tried several deep learning methods but few of them exploited the syntactic information. In this work, we explore the idea of incorporating syntactic parse tree into neural networks. Specifically, we employ the Tree-LSTM model and Tree-GRU model, which are based on the tree structure, to encode the arguments in a relation. Moreover, we further leverage the constituent tags to control the semantic composition process in these tree-structured neural networks. Experimental results show that our method achieves state-of-the-art performance on PDTB corpus.