Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification

• DOI: 10.24963/ijcai.2018/597
• Publication Date: 2018-07-05T05:49:10Z
• Authors: Zhong Qian; Peifeng Li; Yue Zhang; Guodong Zhou; Qiaoming Zhu
• Keywords: Identification; Generative adversarial network; Generative model

Event factuality identification is an important semantic task in NLP. Traditional research heavily relies on annotated texts. This paper proposes a two-step framework, first extracting essential factors related with event from raw texts as the input, and then identifying of events via Generative Adversarial Network Auxiliary Classification (AC-GAN). The use AC-GAN allows model to learn more syntactic information address imbalance among values. Experimental results FactBank show that our method significantly outperforms several state-of-the-art baselines, particularly embedded sources, speculative negative