CONTAINER: Few-Shot Named Entity Recognition via Contrastive Learning

104Citations
Citations of this article
133Readers
Mendeley users who have this article in their library.

Abstract

Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects generalizability to unseen target domains, resulting in suboptimal performances. To this end, we present CONTAINER, a novel contrastive learning technique that optimizes the inter-token distribution distance for Few-Shot NER. Instead of optimizing class-specific attributes, CONTAINER optimizes a generalized objective of differentiating between token categories based on their Gaussian-distributed embeddings. This effectively alleviates overfitting issues originating from training domains. Our experiments in several traditional test domains (OntoNotes, CoNLL'03, WNUT'17, GUM) and a new large scale Few-Shot NER dataset (Few-NERD) demonstrate that, on average, CONTAINER outperforms previous methods by 3%-13% absolute F1 points while showing consistent performance trends, even in challenging scenarios where previous approaches could not achieve appreciable performance. The source code of CONTAINER will be available at: https://github.com/psunlpgroup/CONTaiNER.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Snigdha, S., Das, S., Katiyar, A., Passonneau, R. J., & Zhang, R. (2022). CONTAINER: Few-Shot Named Entity Recognition via Contrastive Learning. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (Vol. 1, pp. 6338–6353). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.acl-long.439

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 34

67%

Researcher 11

22%

Professor / Associate Prof. 3

6%

Lecturer / Post doc 3

6%

Readers' Discipline

Tooltip

Computer Science 49

84%

Linguistics 6

10%

Engineering 2

3%

Philosophy 1

2%

Save time finding and organizing research with Mendeley

Sign up for free