DEEDP: Document-Level Event Extraction Model Incorporating Dependency Paths

Document-level event extraction (DEE) aims at extracting records from given documents. Existing DEE methods handle troublesome challenges by using multiple encoders and casting the task into a multi-step paradigm. However, most of previous approaches ignore missing feature mean pooling or max operations in different encoding stages have not explicitly modeled interdependency features between input tokens, thus long-distance problem cannot be solved effectively. In this study, we propose Event Extraction Model Incorporating Dependency Paths (DEEDP), which introduces novel multi-granularity encoder framework to tackle aforementioned problems. Specifically, first designed Transformer-based encoder, Transformer-M, adding Syntactic Feature Attention mechanism Transformer, can capture more information tokens help enhance semantics for sentence-level representations entities. We then stacked Transformer-M Transformer integrate document-level features; obtained semantic enhanced document-aware each entity model dependencies arguments. Experimental results on benchmarks MUC-4 ChFinAnn demonstrate that DEEDP achieves superior performance over baselines, proving effectiveness our proposed methods.