Prompt-based methods have been successfully applied in sentence-level few-shot learning
tasks, mostly owing to the sophisticated design of templates and label words. However …

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 …

Recent Weak Supervision (WS) approaches have had widespread success in easing the
bottleneck of labeling training data for machine learning by synthesizing labels from multiple …

Distance metric learning has become a popular solution for few-shot Named Entity
Recognition (NER). The typical setup aims to learn a similarity metric for measuring the …

Fine-tuned pre-trained language models (LMs) have achieved enormous success in many
natural language processing (NLP) tasks, but they still require excessive labeled data in the …

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 …

High-quality phrase representations are essential to finding topics and related terms in
documents (aka topic mining). Existing phrase representation learning methods either …

Few-shot NER needs to effectively capture information from limited instances and transfer
useful knowledge from external resources. In this paper, we propose a self-describing …

Prompt tuning has achieved great success in various sentence-level classification tasks by
using elaborated label word mappings and prompt templates. However, for solving token …

Recent years have seen an exponential growth (+ 98% in 2022 wrt the previous year) of the
number of research articles in the few-shot learning field, which aims at training machine …