Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification
This addresses the problem of classifying discourse relations without explicit connectives for natural language processing applications, representing a strong specific gain.
The paper tackles the challenge of implicit discourse relation classification by proposing a feature imitation framework where an implicit relation network learns from a network with access to connectives, achieving state-of-the-art performance on the PDTB benchmark.
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.