Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
arXiv:1803.01165
Abstract
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.
arXiv commentAccepted by IJCNLP 2017, 10 pages
References in corpus (6)
- Enhanced LSTM for Natural Language Inference
- When Are Tree Structures Necessary for Deep Learning of Representations?
- Tree-to-Sequence Attentional Neural Machine Translation
- One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations
- Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attention
- Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification