Few-shot NER
35 papers with code • 4 benchmarks • 4 datasets
Few-Shot Named Entity Recognition (NER) is the task of recognising a 'named entity' like a person, organization, time and so on in a piece of text e.g. "Alan Mathison [person] visited the Turing Institute [organization] in June [time].
Benchmarks
These leaderboards are used to track progress in Few-shot NER
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
WNUT 2017
Few-NERD
Most implemented papers
Simple Questions Generate Named Entity Recognition Datasets
dmis-lab/gener
•
•
Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities.
QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition
dayyass/QaNER
•
•
Recently, prompt-based learning for pre-trained language models has succeeded in few-shot Named Entity Recognition (NER) by exploiting prompts as task guidance to increase label efficiency.
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks.
Label Semantics for Few Shot Named Entity Recognition
TianWuYuJiangHenShou/LabelSemantics
•
•
Findings (ACL) 2022
We study the problem of few shot learning for named entity recognition.
Few-shot Named Entity Recognition with Self-describing Networks
In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set.
Decomposed Meta-Learning for Few-Shot Named Entity Recognition
microsoft/vert-papers
•
•
Findings (ACL) 2022
Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples.
mGPT: Few-Shot Learners Go Multilingual
ai-forever/mgpt
•
•
Recent studies report that autoregressive language models can successfully solve many NLP tasks via zero- and few-shot learning paradigms, which opens up new possibilities for using the pre-trained language models.
Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition
Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks.
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
lifan-yuan/factmix
•
•
COLING 2022
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years.
SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition
unveiled-the-red-hat/SEE-Few
•
•
COLING 2022
Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used.
