Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification

Zhong Qian, Peifeng Li, Yue Zhang, Guodong Zhou, Qiaoming Zhu

IJCAI 2018 pp. 4293-4300

doi:10.24963/IJCAI.2018/597 /ijcai/2018/qian2018ijcai-event/

Abstract

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 factuality from raw texts as the input, and then identifying the factuality of events via a Generative Adversarial Network with Auxiliary Classification (AC-GAN). The use of AC-GAN allows the model to learn more syntactic information and address the imbalance among factuality values. Experimental results on FactBank show that our method significantly outperforms several state-of-the-art baselines, particularly on events with embedded sources, speculative and negative factuality values.

PDF IJCAI Semantic Scholar

Cite

Text

Qian et al. "Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/597

Markdown

[Qian et al. "Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/qian2018ijcai-event/) doi:10.24963/IJCAI.2018/597

BibTeX

@inproceedings{qian2018ijcai-event,
  title     = {{Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification}},
  author    = {Qian, Zhong and Li, Peifeng and Zhang, Yue and Zhou, Guodong and Zhu, Qiaoming},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {4293-4300},
  doi       = {10.24963/IJCAI.2018/597},
  url       = {https://mlanthology.org/ijcai/2018/qian2018ijcai-event/}
}