Event Causality Extraction with Event Argument Correlations
This work addresses a more challenging task for event causality understanding in natural language processing, but it appears incremental as it builds upon existing event causality identification by adding structured extraction.
The authors tackled the problem of extracting cause-effect event pairs with structured event information from text, proposing a dual grid tagging scheme that captures intra- and inter-event argument correlations, and their method demonstrated effectiveness in experiments.
Event Causality Identification (ECI), which aims to detect whether a causality relation exists between two given textual events, is an important task for event causality understanding. However, the ECI task ignores crucial event structure and cause-effect causality component information, making it struggle for downstream applications. In this paper, we explore a novel task, namely Event Causality Extraction (ECE), aiming to extract the cause-effect event causality pairs with their structured event information from plain texts. The ECE task is more challenging since each event can contain multiple event arguments, posing fine-grained correlations between events to decide the causeeffect event pair. Hence, we propose a method with a dual grid tagging scheme to capture the intra- and inter-event argument correlations for ECE. Further, we devise a event type-enhanced model architecture to realize the dual grid tagging scheme. Experiments demonstrate the effectiveness of our method, and extensive analyses point out several future directions for ECE.