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

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2636–2645 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 2636 Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification Pengfei Cao1,2∗, Yubo Chen1,2∗, Yuqing Yang1,3, Kang Liu1,2 and Jun Zhao1,2 1National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3School of Computer Science, Fudan University {pengfei.cao, yubo.chen, kliu, jzhao}@nlpr.ia.ac.cn, yuqingyang21@m.fudan.edu.cn Abstract Event factuality indicates the degree of cer- tainty 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 differ- ent 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 im- portant characteristics: Local Uncertainty and Global Structure, which can be utilized to im- prove performance. In this paper, we pro- pose an Uncertain Local-to-Global Network (ULGN) to make use of these two character- istics. Specifically, we devise a Local Uncer- tainty Estimation module to model the uncer- tainty of local information. Moreover, we pro- pose an Uncertain Information Aggregation module to leverage the global structure for in- tegrating the local information. Experimen- tal 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. 1 Introduction Event factuality refers to the degree of certainty about whether events actually occur or not in the real world. Generally, event factuality can be clas- sified into five categories (Saurı, 2008): Certain Positive (certainly happening, denoted as CT+), Certain Negative (certainly not happening, CT-), Possible Positive (possibly happening, PS+), Possi- ble Negative (possibly not happening, PS-) and Un- derspecified (events’ factuality cannot be identified, Uu). For example, in the sentence “An economist thinks that the tax rate probably increases soon”, the event “increases” may happen. Therefore, an event factuality identification (EFI) model should ∗Equal contribution. Event: United States reaches an agreement with Mexico Text: According to Politico.com, the United States probably reaches (PS+) an agreement with Mexico on the new trade deal before December, 2017. [S1] However, Mexican Economy Minister Ildefonso Guajardo denied that they plan to reach (CT-) any agreement with the U.S. on the trade deal talks. [S2] A journalist agreed the view, said the two sides may reach (PS+) an agreement within hours. [S3] The government has not been informed that any agreement will be reached (CT-) yet, said another two Mexican officials. [S4] Some media speculate that they will possibly reach (PS+) an agreement. [S8] Document-level Event Factuality: CT- Figure 1: An example document with both sentence- and document-level event factuality. The factuality be- tween sentence- and document-level may be different. be able to predict the factuality of the event is PS+. EFI is an important task in natural language pro- cessing (NLP) area, which is …

Content truncated to 500 words