Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
Event extraction is typically modeled as a multi-class classification problem where both event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We propose a novel event extraction framework that takes both event types and argument roles as natural language queries to extract candidate triggers and arguments from the input text. With the rich semantics in the queries, our framework benefits from the attention mechanisms to better capture the semantic correlation between the event types or argument roles and the input text. Furthermore, the query-and-extract formulation allows our approach to leverage all available event annotations from various ontologies as a unified model. Experiments on two public benchmark datasets, ACE and ERE, demonstrate that our approach achieves the state-of-the-art performance on each dataset and significantly outperforms existing methods on zero-shot event extraction. We will make all the programs publicly available once the paper is accepted.
Code (0)
등록된 구현이 없습니다.
Tasks
Event ExtractionMulti-class ClassificationNatural Language QueriesVocal Bursts Type PredictionZero-shot Event ExtractionSimilar Papers 제목 키워드 기반
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We pro…
Event ExtractionMulti-class ClassificationNatural Language QueriesVocal Bursts Type Prediction+1Towards Few-Shot Event Mention Retrieval: An Evaluation Framework and A Siamese Network Approach
Automatically analyzing events in a large amount of text is crucial for situation awareness and decision making. Previous approaches treat event extraction as {``}one size fits all{''} with an ontology defined a priori. …
Decision MakingEvent ExtractionRetrievalProbing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction
We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervi…
Event DetectionEvent ExtractionNatural Language InferenceReading ComprehensionQO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples
Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimi…
Question AnsweringJoint Modeling for Query Expansion and Information Extraction with Reinforcement Learning
Information extraction about an event can be improved by incorporating external evidence. In this study, we propose a joint model for pseudo-relevance feedback based query expansion and information extraction with reinfo…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1