Event Extraction
9개 벤치마크 · 논문 473편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
Event Extraction by Answering (Almost) Natural Questions
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
Are Triggers Needed for Document-Level Event Extraction?
Event Extraction as Question Generation and Answering
Papers
A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework
Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-specific designs, limiting scalability and cross-domain generalizati…
Information ExtractionDomain GeneralizationEvent ExtractionA Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction
Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations. Despite strong in-domain performance, developing models that generalize robustl…
Domain GeneralizationEvent ExtractionLA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction
Large language models show strong promise for information extraction (IE), but existing reflection-based correction methods are often misaligned with structured extraction outputs. Free-form self-reflection can flag an e…
Information ExtractionReinforcement LearningRelation ExtractionEvent ExtractionGrounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy
Form 8-K filings are the primary channel through which U.S. public companies disclose material events, but the SEC item codes attached to them are coarse: a single item spans routine administrative changes and chief exec…
Event ExtractionEvaluation Pitfalls and Challenges in Multimedia Event Extraction
Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understanding. While recent work reports steady and…
Event ExtractionSAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction
Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for understanding multimedia content but remai…
Information ExtractionRelation ExtractionData AugmentationEvent Extraction