Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification

TL;DR

This paper introduces an adversarial feature imitation framework that leverages connectives to improve implicit discourse relation classification, achieving state-of-the-art results on the PDTB benchmark.

Contribution

It presents a novel adversarial network approach that transfers connective discriminability to implicit relation classification models.

Findings

Achieves state-of-the-art performance on PDTB benchmark.

Effective transfer of connective features to implicit relation models.

Adversarial training enhances classification accuracy.

Abstract

Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark.