Document-Level Event Argument Extraction by Conditional Generation
This addresses the limitation of sentence-level event extraction for information retrieval, providing more complete results for users needing detailed event information.
The paper tackles the problem of incomplete event extraction by proposing a document-level neural model for event argument extraction, achieving absolute F1 gains of 7.6% and 5.7% over the next best model on RAMS and WikiEvents datasets, and a 9.3% F1 gain on informative argument extraction.
Event extraction has long been treated as a sentence-level task in the IE community. We argue that this setting does not match human information-seeking behavior and leads to incomplete and uninformative extraction results. We propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates. We also compile a new document-level event extraction benchmark dataset WikiEvents which includes complete event and coreference annotation. On the task of argument extraction, we achieve an absolute gain of 7.6% F1 and 5.7% F1 over the next best model on the RAMS and WikiEvents datasets respectively. On the more challenging task of informative argument extraction, which requires implicit coreference reasoning, we achieve a 9.3% F1 gain over the best baseline. To demonstrate the portability of our model, we also create the first end-to-end zero-shot event extraction framework and achieve 97% of fully supervised model's trigger extraction performance and 82% of the argument extraction performance given only access to 10 out of the 33 types on ACE.