CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
Sarkar Snigdha Sarathi Das, Arzoo Katiyar, Rebecca Passonneau, Rui Zhang
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.- Anthology ID:
- 2022.acl-long.439
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6338–6353
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.439
- DOI:
- 10.18653/v1/2022.acl-long.439
- Cite (ACL):
- Sarkar Snigdha Sarathi Das, Arzoo Katiyar, Rebecca Passonneau, and Rui Zhang. 2022. CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6338–6353, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning (Das et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.439.pdf
- Code
- psunlpgroup/container
- Data
- Few-NERD, WNUT 2017