Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning

About

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.

Sarkar Snigdha Sarathi Das, Arzoo Katiyar, Rebecca J. Passonneau, Rui Zhang• 2021

Related benchmarks

TaskDatasetResultRank
Named Entity RecognitionCoNLL 2003 (test)--
539
Named Entity RecognitionCoNLL 03--
102
Named Entity RecognitionWnut 2017--
79
Named Entity RecognitionWNUT 2017 (test)--
63
Named Entity RecognitionFew-NERD INTER 1.0 (test)
Average F161.83
62
Named Entity RecognitionFewNERD INTRA
F1 Score57.83
47
Few-shot Named Entity RecognitionFewNERD Intra 1.0
F1 Score53.7
44
Few-shot Named Entity RecognitionFew-NERD Intra (test)
F1 Score53.7
40
Named Entity RecognitionNCBI-disease (test)--
40
Named Entity RecognitionGUM
Micro F124.4
36
Showing 10 of 21 rows

Other info

Code

Follow for update