Prompt-Based Metric Learning for Few-Shot NER
This work addresses the challenge of generalizing to unseen labels or domains with limited data for NER, representing an incremental improvement over existing metric learning methods.
The paper tackles the problem of few-shot named entity recognition by improving metric learning to better incorporate label semantics, achieving new state-of-the-art results with an average relative gain of 8.84% in micro F1 across most settings.
Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to fully incorporate label semantics into modeling. To address this issue, we propose a simple method to largely improve metric learning for NER: 1) multiple prompt schemas are designed to enhance label semantics; 2) we propose a novel architecture to effectively combine multiple prompt-based representations. Empirically, our method achieves new state-of-the-art (SOTA) results under 16 of the 18 considered settings, substantially outperforming the previous SOTA by an average of 8.84% and a maximum of 34.51% in relative gains of micro F1. Our code is available at https://github.com/AChen-qaq/ProML.