论文标题
及时基于少量的公制学习
Prompt-Based Metric Learning for Few-Shot NER
论文作者
论文摘要
几个命名的实体识别（NER）的目标是概括为看不见的标签和/或域，几乎没有标记的示例。现有的度量学习方法计算查询和支持集之间的令牌级别相似性，但无法将标签语义完全纳入建模。为了解决这个问题，我们提出了一种简单的方法来在很大程度上改善NER的度量学习：1）多个提示模式旨在增强标签语义； 2）我们提出了一种新颖的体系结构，以有效地结合了多个基于快速的表示。从经验上讲，我们的方法在18种考虑的设置下实现了新的最新结果（SOTA）结果，其表现平均超过了先前的SOTA 8.84％，而微型F1的相对增长率最高为34.51％。我们的代码可在https://github.com/achen-qaq/proml上找到。
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.
