Zero-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 predefined event types as heuristic rules or resort to external semantic analyzing tools. To overcome this weakness, we propose an end-to-end framework named Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction (ZEOP). By creatively introducing multiple contrastive samples with ordered similarities, the encoder can learn event representations from both instance-level and class-level, which makes the distinctions between different unseen types more significant. Meanwhile, we utilize the prompt-based prediction to identify trigger words without relying on external resources. Experiments demonstrate that our model detects events more effectively and accurately than state-of-the-art methods.
Code (1)
Tasks
Contrastive LearningEvent DetectionSimilar Papers 제목 키워드 기반
Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning
With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for trai…
Event DetectionMeta-LearningZero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning
Event Causality Identification (ECI) refers to the detection of causal relations between events in texts. However, most existing studies focus on sentence-level ECI with high-resource languages, leaving more challenging …
Event Causality IdentificationFew-Shot LearningSentenceTransfer LearningContrastive Feature Masking Open-Vocabulary Vision Transformer
We present Contrastive Feature Masking Vision Transformer (CFM-ViT) - an image-text pretraining methodology that achieves simultaneous learning of image- and region-level representation for open-vocabulary object detecti…
Contrastive LearningImage-text Retrievalobject-detectionObject Detection+4mCPT at SemEval-2023 Task 3: Multilingual Label-Aware Contrastive Pre-Training of Transformers for Few- and Zero-shot Framing Detection
This paper presents the winning system for the zero-shot Spanish framing detection task, which also achieves competitive places in eight additional languages. The challenge of the framing detection task lies in identifyi…
The 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 Prediction