Event Causality Identification with Causal News Corpus -- Shared Task 3, CASE 2022

TL;DR

This paper summarizes the results of the CASE 2022 shared task on event causality identification, highlighting top approaches using fine-tuned pre-trained language models and analyzing system performances.

Contribution

It provides a comprehensive overview of the shared task, including participant results, top methods, and error analysis for event causality detection in news texts.

Findings

Top F1 score for causal detection was 86.19%.

Top F1 score for span identification was 54.15%.

Pre-trained language models were central to top-performing systems.

Abstract

The Event Causality Identification Shared Task of CASE 2022 involved two subtasks working on the Causal News Corpus. Subtask 1 required participants to predict if a sentence contains a causal relation or not. This is a supervised binary classification task. Subtask 2 required participants to identify the Cause, Effect and Signal spans per causal sentence. This could be seen as a supervised sequence labeling task. For both subtasks, participants uploaded their predictions for a held-out test set, and ranking was done based on binary F1 and macro F1 scores for Subtask 1 and 2, respectively. This paper summarizes the work of the 17 teams that submitted their results to our competition and 12 system description papers that were received. The best F1 scores achieved for Subtask 1 and 2 were 86.19% and 54.15%, respectively. All the top-performing approaches involved pre-trained language models fine-tuned to the targeted task. We further discuss these approaches and analyze errors across participants' systems in this paper.