This paper presents an empirical study to efficiently build named entity recognition (NER)
systems when a small amount of in-domain labeled data is available. Based upon recent …

This paper presents a comprehensive study to efficiently build named entity recognition
(NER) systems when a small number of in-domain labeled data is available. Based upon …

We develop a transductive meta-learning method that uses unlabelled instances to improve
few-shot image classification performance. Our approach combines a regularized …

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled
instances. Many few-shot visual recognition methods adopt the metric-based meta-learning …

With tremendous amounts of texts across the Internet nowadays, it is incredibly difficult for
people to manually seek for valuable knowledge from massive corpora, thus automatic …

Few-shot classification aims to recognize query samples from novel classes given scarce
labeled data, which remains a challenging problem in machine learning. This paper …

Metric-based few-shot learning (FSL) methods have been attracting more and more
research attention since they reflect a simpler and more effective inductive bias in the limited …

RelationNet is a highly effective metric-based few-shot learning method. However,
RelationNet uses only shallow convolutional networks in the feature extraction stage …

Among various supervised deep metric learning methods proxy-based approaches have
achieved high retrieval accuracies. Proxies, which are class-representative points in an …

The scarcity of resources, lack of labeled texts, and insufficient corpora pose significant
challenges to many specialized classification problems. It increases the difficulty of small …