Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3651–3661 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 3651 Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction Amir Pouran Ben Veyseh1, Tuan Ngo Nguyen1 and Thien Huu Nguyen1,2 1 Department of Computer and Information Science, University of Oregon, Eugene, OR 97403, USA 2 VinAI Research, Vietnam {apouranb,tnguyen,thien}@cs.uoregon.edu Abstract The goal of Event Argument Extraction (EAE) is to find the role of each entity mention for a given event trigger word. It has been shown in the previous works that the syntactic structures of the sentences are helpful for the deep learn- ing models for EAE. However, a major prob- lem in such prior works is that they fail to ex- ploit the semantic structures of the sentences to induce effective representations for EAE. Con- sequently, in this work, we propose a novel model for EAE that exploits both syntactic and semantic structures of the sentences with the Graph Transformer Networks (GTNs) to learn more effective sentence structures for EAE. In addition, we introduce a novel inductive bias based on information bottleneck to improve generalization of the EAE models. Exten- sive experiments are performed to demonstrate the benefits of the proposed model, leading to state-of-the-art performance for EAE on stan- dard datasets. 1 Introduction Event Extraction (EE) is an important task of In- formation Extraction that aims to recognize events and their arguments in text. In the literature, EE is often divided into two sub-tasks: (1) Event De- tection (ED) to detect the event trigger words, and (2) Event Argument Extraction (EAE) to identity the event arguments and their roles for the given event triggers. In recent years, ED has been stud- ied extensively with deep learning while EAE is relatively less explored (Wang et al., 2019b). As EAE is necessary to accomplish EE and helpful for many downstream applications (Yang et al., 2003; Cheng and Erk, 2018), further studies are required to improve the performance of EAE. This work focuses on EAE to meet this requirement for EE. The current state-of-the-art methods for EAE have involved deep learning models that compute an abstract representation vector for each word in the input sentences based on the information from the other context words. The representation vec- tors for the words are then aggregated to perform EAE (Chen et al., 2015; Nguyen et al., 2016). Our main motivation in this work is to exploit differ- ent structures in the input sentences to improve the representation vectors for the words in the deep learning models for EAE. In this work, a sentence structure (or view) refers to an importance score matrix whose cells quantify the contribution of a context word for the representation vector compu- tation of the current word for EAE. In particular, we consider two types of sentence structures in this work, i.e., syntactic and semantic structures. As such, the importance score for a pair of words in the syntactic structures is determined by the …

Content truncated to 500 words