Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem. To tackle the issue of low sample diversity in few-shot ED, we propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge as the knowledge prior of event types. Furthermore, as external knowledge typically provides limited and imperfect coverage of event types, we introduce an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust the knowledge prior of event types. Experiments show our method consistently and substantially outperforms a number of baselines by at least 15 absolute F1 points under the same few-shot settings.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityEvent DetectionFew-Shot LearningMeta-LearningSimilar Papers 제목 키워드 기반
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is f…
Bayesian InferenceMeta-LearningVariational InferenceVariadic Learning by Bayesian Nonparametric Deep Embedding
Learning at small or large scales of data is addressed by two strong but divided frontiers: few-shot learning and standard supervised learning. Few-shot learning focuses on sample efficiency at small scale, while supervi…
ClusteringFew-Shot LearningMeta-LearningMetric LearningMeta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning
We introduce Meta-AdaM, a meta-learned adaptive optimizer with momentum, designed for few-shot learning tasks that pose significant challenges to deep learning models due to the limited number of labeled examples. Meta-l…
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
Few-shot segmentation~(FSS) performance has been extensively promoted by introducing episodic training and class-wise prototypes. However, the FSS problem remains challenging due to three limitations: (1) Models are dist…
COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detection
Most Fake News Detection (FND) methods often struggle with data scarcity for emerging news domain. Recently, prompt learning based on Pre-trained Language Models (PLM) has emerged as a promising approach in domain adapti…
Fake News DetectionFew-Shot LearningPrompt Learning