Implicit Discourse Relation Classification via Multi-Task Neural Networks
This work addresses a bottleneck in discourse parsing for natural language processing, though it is incremental as it builds on existing frameworks.
The paper tackled the challenging task of implicit discourse relation classification without connectives by proposing a multi-task neural network that leverages multiple discourse corpora, achieving significant gains over baseline systems on the PDTB dataset.
Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation frameworks, there exist multiple corpora which have internal connections. To exploit the combination of different discourse corpora, we design related discourse classification tasks specific to a corpus, and propose a novel Convolutional Neural Network embedded multi-task learning system to synthesize these tasks by learning both unique and shared representations for each task. The experimental results on the PDTB implicit discourse relation classification task demonstrate that our model achieves significant gains over baseline systems.