Adversarial connective-exploiting networks for implicit discourse relation classification????(Open Access)

作者：Qin, Lianhui; Zhang, Zhisong; Zhao, Hai^*; Hu, Zhiting; Xing, Eric P

来源：55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, 2017-07-30 To 2017-08-04.

DOI：10.18653/v1/P17-1093

• Discriminability
• Implicit features
• Relation classifications
• Salient features
• State-of-the-art performance

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.

• 出版日期2017
• 单位上海交通大学