Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4393–4399 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 4393 Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures Amir Pouran Ben Veyseh, Thien Huu Nguyen and Dejing Dou Department of Computer and Information Science University of Oregon Eugene, OR 97403, USA {apouranb, thien, dou}@cs.uoregon.edu Abstract Event factuality prediction (EFP) is the task of assessing the degree to which an event men- tioned in a sentence has happened. For this task, both syntactic and semantic information are crucial to identify the important context words. The previous work for EFP has only combined these information in a simple way that cannot fully exploit their coordination. In this work, we introduce a novel graph-based neural network for EFP that can integrate the semantic and syntactic information more ef- fectively. Our experiments demonstrate the advantage of the proposed model for EFP. 1 Introduction Events are often presented in sentences via the indication of anchor/trigger words (i.e., the main words to evoke the events, called event mentions) (Nguyen et al., 2016a). Event mentions can ap- pear with varying degrees of uncertainty/factuality to reflect the intent of the writers. In order for the event mentions to be useful (i.e., for knowl- edge extraction tasks), it is important to determine their factual certainty so the actual event mentions can be retrieved (i.e., the event factuality predic- tion problem (EFP)). In this work, we focus on the recent regression formulation of EFP that aims to predict a real score in the range of [-3,+3] to quan- tify the occurrence possibility of a given event mention (Stanovsky et al., 2017; Rudinger et al., 2018). This provides more meaningful informa- tion for the downstream tasks than the classifica- tion formulation of EFP (Lee et al., 2015). For instance, the word “left” in the sentence “She left yesterday.” would express an event that certainly happened (i.e., corresponding to a score of +3 in the benchmark datasets) while the event mention associated with “leave” in the sentence “She for- got to leave yesterday.” would certainly not hap- pen (i.e., a score of -3). go I will seeing after treatment the others of need when I care medical back Figure 1: The dependency tree of the sentence “I will, after seeing the treatment of others, go back when I need medical care.”. EFP is a challenging problem as different con- text words might jointly participate to reveal the factuality of the event mentions (i.e., the cue words), possibly located at different parts of the sentences and scattered far away from the anchor words of the events. There are two major mech- anisms that can help the models to identify the cue words and link them to the anchor words, i.e., the syntactic trees (i.e., the dependency trees) and the semantic information (Rudinger et al., 2018). For the syntactic trees, they can connect the an- chor words to the functional words …

Content truncated to 500 words