Knowledge Graph Enhanced Event Extraction in Financial Documents

Abstract

Event extraction is a classic task in natural language processing with wide use in handling large amount of yet rapidly growing financial, legal, medical, and government documents which often contain multiple events with their elements scattered and mixed across the documents, making the problem much more difficult. Though the underlying relations between event elements to be extracted provide helpful contextual information, they are somehow overlooked in prior studies.We showcase the enhancement to this task brought by utilizing the knowledge graph that captures entity relations and their attributes. Beyond straightforward feature engineering attempts, we propose a first event extraction framework that embeds a knowledge graph through a Graph Neural Network and integrates the embedding with regular features, all at document-level. Specifically, for extracting events from Chinese financial announcements, our method outperforms the state-of-the-art method by 5.3% in F1-score. Specifically, our method demonstrates its effectiveness in improving the performance of multiple events extraction. Besides, we make the lawsuit event dataset public to facilitate relevant research.