Implicit Discourse Relation Classification via Multi-Task Neural Networks

Abstract

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.

arXiv commentThis is the pre-print version of a paper accepted by AAAI-16

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (12)

• Multi-Task Learning in Natural Language Processing: An Overview
• DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion
• An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis
• On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification
• Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
• DiscSense: Automated Semantic Analysis of Discourse Markers
• Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification
• Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media
• ISS-MULT: Intelligent Sample Selection for Multi-Task Learning in Question Answering
• Semantically Driven Sentence Fusion: Modeling and Evaluation
• Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification
• Unifying Discourse Resources with Dependency Framework