CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction
This addresses a realistic problem in information extraction for NLP applications, but it is incremental as it builds on existing event extraction methods.
The paper tackles overlapping event extraction, where words can serve multiple roles, by proposing CasEE, a joint learning framework with cascade decoding that sequentially handles type detection, trigger extraction, and argument extraction. It achieves significant improvements on the FewFC benchmark over previous methods.
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without overlaps, which are not applicable to the complicated overlapping event extraction. This work systematically studies the realistic event overlapping problem, where a word may serve as triggers with several types or arguments with different roles. To tackle the above problem, we propose a novel joint learning framework with cascade decoding for overlapping event extraction, termed as CasEE. Particularly, CasEE sequentially performs type detection, trigger extraction and argument extraction, where the overlapped targets are extracted separately conditioned on the specific former prediction. All the subtasks are jointly learned in a framework to capture dependencies among the subtasks. The evaluation on a public event extraction benchmark FewFC demonstrates that CasEE achieves significant improvements on overlapping event extraction over previous competitive methods.