paper-with-me

홈 › Papers

Prompt-Guided Few-Shot Event Detection

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Event DetectionEvent ExtractionFew-Shot Learning

Similar Papers 제목 키워드 기반

P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization

2022-02-15 · Sha Li, Liyuan Liu, Yiqing Xie, Heng Ji 외

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+2

The Art of Prompting: Event Detection based on Type Specific Prompts

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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 Prediction

The Art of Prompting: Event Detection based on Type Specific Prompts

2022-04-14 · Sijia Wang, Mo Yu, Lifu Huang

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 Prediction

Can GPT-4 Models Detect Misleading Visualizations?

2024-08-08 · Jason Alexander, Priyal Nanda, Kai-Cheng Yang, Ali Sarvghad

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 Engineering

Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction

2022-07-01 · Findings (NAACL) 2022 7 · Senhui Zhang, Tao Ji, Wendi Ji, Xiaoling Wang

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