Prompt-Guided Few-Shot Event Detection
Practical applications of event extraction systems have long been hindered by their need for heavy human annotation. In order to scale up to new domains and event types, models must learn to cope with limited supervision, as in few-shot learning settings. To this end, the major challenge is to let the model master the semantic of event types, without requiring abundant event mention annotations. In our study, we employ cloze prompts to elicit event-related knowledge from pre-trained language models and further use event definitions and keywords to pinpoint the trigger word. By formulating the event detection task as an "identify-then-localize" procedure, we minimize the number of type-specific parameters, enabling our model to quickly adapt to event detection tasks for new types. Experiments on three event detection benchmark datasets (ACE, FewEvent, MAVEN) show that our proposed method performs favorably under fully supervised settings and surpasses existing few-shot methods by 16% F1 on the FewEvent dataset and 23% on the MAVEN dataset when only 5 examples are provided for each event type.
Code (0)
등록된 구현이 없습니다.
Tasks
Event DetectionEvent ExtractionFew-Shot LearningSimilar Papers 제목 키워드 기반
P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization
We propose P4E, an identify-and-localize event detection framework that integrates the best of few-shot prompting and structured prediction. Our framework decomposes event detection into an identification task and a loca…
Event DetectionEvent ExtractionFew-Shot LearningMulti-Label Classification+2The Art of Prompting: Event Detection based on Type Specific Prompts
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental result…
Event DetectionVocal Bursts Type PredictionThe Art of Prompting: Event Detection based on Type Specific Prompts
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental result…
Event DetectionVocal Bursts Type PredictionCan GPT-4 Models Detect Misleading Visualizations?
The proliferation of misleading visualizations online, particularly during critical events like public health crises and elections, poses a significant risk. This study investigates the capability of GPT-4 models (4V, 4o…
MisinformationPrompt EngineeringZero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction
Event detection is a classic natural language processing task. However, the constantly emerging new events make supervised methods not applicable to unseen types. Previous zero-shot event detection methods either require…
Contrastive LearningEvent Detection