Few-shot Named Entity Recognition: Definition, Taxonomy and Research Directions
Распознавание именованных сущностей в условиях малых выборок: определение, таксономия и направления исследований
2023-07-18
SCID: 54.1/vpy9t272
Discuss with AI
few-shot learningfew-shot named entity recognitionknowledge graphslow-resource languagesmodel-centric and data-centric methods
Figures from the paper
Abstract (AI)
Recent years have seen an exponential growth (+98% in 2022 w.r.t. the previous year) of the number of research articles in the few-shot learning field, which aims at training machine learning models with extremely limited available data. The research interest toward few-shot learning systems for Named Entity Recognition (NER) is thus at the same time increasing. NER consists in identifying mentions of pre-defined entities from unstructured text, and serves as a fundamental step in many downstream tasks, such as the construction of Knowledge Graphs, or Question Answering. The need for a NER system able to be trained with few-annotated examples comes in all its urgency in domains where the annotation process requires time, knowledge and expertise (e.g., healthcare, finance, legal), and in low-resource languages. In this survey, starting from a clear definition and description of the few-shot NER (FS-NER) problem, we take stock of the current state-of-the-art and propose a taxonomy which divides algorithms in two macro-categories according to the underlying mechanisms: model-centric and data-centric. For each category, we line-up works as a story to show how the field is moving toward new research directions. Eventually, techniques, limitations, and key aspects are deeply analyzed to facilitate future studies.
Key Findings
1
A taxonomy categorizes few-shot NER algorithms into model-centric and data-centric approaches based on their underlying mechanisms.
2
Few-shot NER addresses entity recognition with extremely limited annotated data, particularly relevant to specialized domains and low-resource languages.
3
The survey analyzes techniques, limitations, and key aspects of few-shot NER to support future research.
4
The survey provides a clear definition and description of the few-shot NER problem and reviews its current state of the art.
5
The surveyed research is organized to illustrate the field’s evolution toward emerging research directions.
Research Object
few-shot Named Entity Recognition systems
Research Subject
the definition, taxonomy, state of the art, techniques, limitations, and research directions of few-shot NER
Publication Details
Publication Date
2023-07-18
Journal
ACM Transactions on Intelligent Systems and Technology
Publisher
Association for Computing Machinery
ISSN
2157-6904
Cited by
41
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
Proceedings of the 24th international conference on Machine learning2007
Transformers: State-of-the-Art Natural Language Processing2020
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks2019
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing2021
Evaluating Large Language Models Trained on Code2021
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction2018