EDM3: Event Detection as Multi-task Text Generation
Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar, Kuntal Kumar Pal, Chitta R. Baral · 2024
We present EDM3, a novel approach for Event Detection (ED) based on decomposing and reformulating ED, and fine-tuning over its atomic subtasks.EDM3 enhances knowledge transfer while mitigating the error propagation inherent in pipelined approaches.EDM3 infers datasetspecific knowledge required for the complex primary task from its atomic tasks, making it adaptable to any set of event types.We evaluate EDM3 on multiple ED datasets, achieving state-of-the-art results on RAMS (71.3% vs. 65.1% F1), and competitive performance on WikiEvents, MAVEN (∆ = 0.2%), and MLEE (∆ = 1.8%).We present an ablation study over rare event types (<15 instances in training data) in MAVEN, where EDM3 achieves ∼ 90% F1.To the best of the authors' knowledge, we are the first to analyze ED performance over non-standard event configurations (i.e., multiword and multi-class triggers).Experimental results show that EDM3 achieves ∼ 90% exact match accuracy on multi-word triggers and ∼ 61% prediction accuracy on multi-class triggers 1 .This work establishes the effectiveness of EDM3 in enhancing performance on a complex information extraction task.