Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
This addresses the problem of adapting named entity recognition to new domains with limited labeled data, representing a strong incremental improvement over existing methods.
The paper tackles few-shot named entity recognition by proposing a system that combines nearest neighbor learning with structured inference, achieving state-of-the-art performance with F1 score improvements of 6% to 16% over prior meta-learning systems.
We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this feature-space is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves state-of-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by $6\%$ to $16\%$ absolute points over prior meta-learning based systems.