COFFEE: A Contrastive Oracle-Free Framework for Event Extraction
This addresses a more realistic scenario in event extraction for NLP applications, though it is incremental as it builds on existing methods by removing oracle dependencies.
The paper tackles the Oracle-Free Event Extraction (OFEE) task, where events must be extracted from text without prior oracle information like event types, and proposes the COFFEE framework, which outperforms state-of-the-art methods on the ACE05 benchmark.
Event extraction is a complex information extraction task that involves extracting events from unstructured text. Prior classification-based methods require comprehensive entity annotations for joint training, while newer generation-based methods rely on heuristic templates containing oracle information such as event type, which is often unavailable in real-world scenarios. In this study, we consider a more realistic setting of this task, namely the Oracle-Free Event Extraction (OFEE) task, where only the input context is given without any oracle information, including event type, event ontology and trigger word. To solve this task, we propose a new framework, called COFFEE, which extracts the events solely based on the document context without referring to any oracle information. In particular, a contrastive selection model is introduced in COFFEE to rectify the generated triggers and handle multi-event instances. The proposed COFFEE outperforms state-of-the-art approaches under the oracle-free setting of the event extraction task, as evaluated on a public event extraction benchmark ACE05.