arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.04337cs.CL
收藏

Few-Shot NER的尺度学习

Prompt-Based Metric Learning for Few-Shot NER

Tsinghua University(清华大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Qizhi Institute(上海期智研究院)

Yanru Chen, Yanan Zheng, Zhilin Yang

摘要:

Few-Shot命名实体识别(NER)目标,概括为具有很少标记示例的不可见标签和/或域。现有的度量学习方法计算查询和支持集之间的标记级相似性,但不能完全将标签语义纳入建模。为了解决这个问题,我们提出了一个简单的方法,大大提高度量学习NER:1)多提示模式的设计,以增强标签语义; 2)我们提出了一种新的架构,有效地结合多个基于提示的表示。从经验上讲,我们的方法在18个考虑的设置中的16个下实现了新的最先进的(SOTA)结果,在微F1的相对增益方面,平均值为8.84%,最大值为34.51%,大大优于以前的SOTA。我们的代码可在https://github.com/AChen-qaq/ProML上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑