Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework-猫眼课题宝

DOI：

10.18653/v1/2021.findings-emnlp.139

发表时间：

2021-09

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Yaqing Wang;Haoda Chu;Chao Zhang;Jing Gao

在这项工作中，我们研究了命名实体识别（NER）在低资源的情况下，专注于少数拍摄和零拍摄设置的问题。基于大规模的预训练语言模型，我们提出了一种新的NER框架，即SpanNER，它从自然语言监督中学习，并在不使用域内标记数据的情况下识别从未见过的实体类。我们在5个基准数据集上进行了大量的实验，并在少拍学习，域转移和零拍学习设置中评估了所提出的方法。实验结果表明，该方法在少镜头学习、领域转移和零镜头学习设置下，相对于最佳基线，平均性能分别提高了10%、23%和26%。

In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings. Built upon large-scale pre-trained language models, we propose a novel NER framework, namely SpanNER, which learns from natural language supervision and enables the identification of never-seen entity classes without using in-domain labeled data. We perform extensive experiments on 5 benchmark datasets and evaluate the proposed method in the few-shot learning, domain transfer and zero-shot learning settings. The experimental results show that the proposed method can bring 10%, 23% and 26% improvements in average over the best baselines in few-shot learning, domain transfer and zero-shot learning settings respectively.

Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework

文献摘要

相似文献