arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08985cs.CL
收藏

Few Shot命名实体识别的标签语义

Label Semantics for Few Shot Named Entity Recognition

AWS AI Labs(亚马逊云科技人工智能实验室);University of Pennsylvania(宾夕法尼亚大学)

Jie Ma, Miguel Ballesteros, Srikanth Doss, Rishita Anubhai, Sunil Mallya, Yaser Al-Onaizan, Dan Roth

摘要:

研究了命名实体识别的少样本学习问题。具体来说,我们利用标签名称中的语义信息作为一种方式,为模型提供额外的信号和丰富的先验知识。我们提出了一个神经架构,由两个BERT编码器,一个编码的文档和它的令牌和另一个编码的标签在自然语言格式。我们的模型学习将第一个编码器计算的命名实体的表示与第二个编码器计算的标签表示相匹配。标签语义信号被示出为支持多个Few Shot NER基准测试和标准基准测试中的标准性能的改进的最先进的结果。我们的模型在低资源环境中特别有效。

英文摘要:

We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural architecture that consists of two BERT encoders, one to encode the document and its tokens and another one to encode each of the labels in natural language format. Our model learns to match the representations of named entities computed by the first encoder with label representations computed by the second encoder. The label semantics signal is shown to support improved state-of-the-art results in multiple few shot NER benchmarks and on-par performance in standard benchmarks. Our model is especially effective in low resource settings.

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。

↑