Causal Intervention-based Few-Shot Named Entity Recognition

3Citations
Citations of this article
6Readers
Mendeley users who have this article in their library.

Abstract

Few-shot named entity recognition (NER) systems aim to recognize new classes of entities with limited labeled samples. However, these systems face a significant challenge of overfitting compared to tasks with abundant samples. This overfitting is mainly caused by the spurious correlation resulting from the bias in selecting a few samples. To address this issue, we propose a causal intervention-based few-shot NER method in this paper. Our method, based on the prototypical network, intervenes in the context to block the backdoor path between context and label. In the one-shot scenario, where no additional context is available for intervention, we employ incremental learning to intervene on the prototype, which also helps mitigate catastrophic forgetting. Our experiments on various benchmarks demonstrate that our approach achieves new state-of-the-art results.

References Powered by Scopus

Catastrophic forgetting in connectionist networks

1674Citations
N/AReaders
Get full text

Metric learning: A survey

703Citations
N/AReaders
Get full text

Few-shot classification in named entity recognition task

170Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Fighting Against the Repetitive Training and Sample Dependency Problem in Few-Shot Named Entity Recognition

5Citations
N/AReaders
Get full text

Information Extraction in Low-Resource Scenarios: Survey and Perspective

0Citations
N/AReaders
Get full text

Few-shot Named Entity Recognition via encoder and class intervention

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Yang, Z., Liu, Y., & Ouyang, C. (2023). Causal Intervention-based Few-Shot Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 15635–15646). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.findings-emnlp.1046

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 4

80%

Lecturer / Post doc 1

20%

Readers' Discipline

Tooltip

Computer Science 4

67%

Medicine and Dentistry 1

17%

Social Sciences 1

17%

Save time finding and organizing research with Mendeley

Sign up for free