arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.12252cs.CL
收藏

基于自描述网络的Few-Shot命名实体识别

Few-shot Named Entity Recognition with Self-describing Networks

University of Chinese Academy of Sciences(中国科学院大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Beijing Academy of Artificial Intelligence(北京人工智能研究院)

Jiawei Chen, Qing Liu, Hongyu Lin, Xianpei Han, Le Sun

摘要:

Few-Shot NER需要有效地从有限的实例中捕获信息,并从外部资源中传输有用的知识。在本文中,我们提出了一个自我描述机制,Few-Shot NER,它可以有效地利用说明性的实例,并精确地从外部资源的知识,通过描述实体类型和提及使用一个通用的概念集。具体来说,我们设计了自描述网络(SDNet),Seq2Seq生成模型,它可以通用地使用概念描述提及,自动将新的实体类型映射到概念,并按需自适应地识别实体。我们使用大规模语料库对SDNet进行预训练,并在来自不同领域的8个基准上进行实验。实验结果表明,SDNet在所有基准测试中都达到了竞争性的性能,并在6个基准测试中达到了新的最先进水平,这证明了其有效性和鲁棒性。

英文摘要:

Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set. Specifically, we design Self-describing Networks (SDNet), a Seq2Seq generation model which can universally describe mentions using concepts, automatically map novel entity types to concepts, and adaptively recognize entities on-demand. We pre-train SDNet with large-scale corpus, and conduct experiments on 8 benchmarks from different domains. Experiments show that SDNet achieves competitive performances on all benchmarks and achieves the new state-of-the-art on 6 benchmarks, which demonstrates its effectiveness and robustness.

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。

↑