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 …

Document-level Event Factuality Identification via Reinforced Multi-Granularity Hierarchical Attention Networks. ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …

Dec 6, 2025 · To solve these two issues, we first construct a corpus annotated with both document- and sentence-level event factuality information on both English and Chinese texts.

Bibliographic details on Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification.

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 …

Qian, Z., Li, P., Zhang, Y., Zhou, G., Zhu, Q.: Event factuality identification via generative adversarial networks with auxiliary classification. In: IJCAI, pp. 4293– 4300 (2018)

title = {Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification}, author = {Zhong Qian and Peifeng Li and Yue Zhang and Guodong Zhou and Qiaoming Zhu},

We investigated document-level event factuality identification task by constructing a corpus an-notated with document- and sentence-level event factuality based on both English and Chinese texts.

Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI …

Nov 4, 2025 · Zhong Qian, Peifeng Li, Qiaoming Zhu, Guodong Zhou: A multi-view heterogeneous and extractive graph attention network for evidential document-level event factuality identification.