Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification

Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, Jun Zhao


Abstract
Event factuality indicates the degree of certainty about whether an event occurs in the real world. Existing studies mainly focus on identifying event factuality at sentence level, which easily leads to conflicts between different mentions of the same event. To this end, we study the problem of document-level event factuality identification, which determines the event factuality from the view of a document. For this task, we need to consider two important characteristics: Local Uncertainty and Global Structure, which can be utilized to improve performance. In this paper, we propose an Uncertain Local-to-Global Network (ULGN) to make use of these two characteristics. Specifically, we devise a Local Uncertainty Estimation module to model the uncertainty of local information. Moreover, we propose an Uncertain Information Aggregation module to leverage the global structure for integrating the local information. Experimental results demonstrate the effectiveness of our proposed method, outperforming the previous state-of-the-art model by 8.4% and 11.45% of F1 score on two widely used datasets.
Anthology ID:
2021.emnlp-main.207
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2636–2645
Language:
URL:
https://aclanthology.org/2021.emnlp-main.207
DOI:
10.18653/v1/2021.emnlp-main.207
Bibkey:
Cite (ACL):
Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, and Jun Zhao. 2021. Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2636–2645, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification (Cao et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2021.emnlp-main.207.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-3/2021.emnlp-main.207.mp4
Code
 cpf-nlpr/ulgn4docefi