CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
This addresses the challenge of entity tagging in low-resource domains for NLP applications, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the problem of few-shot named entity recognition (NER) by proposing CONTaiNER, a contrastive learning technique that optimizes inter-token distribution distance to improve generalizability to unseen domains, resulting in an average performance gain of 3%-13% absolute F1 points over previous methods.
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.