arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.03353cs.CLcs.IR
收藏

SEPT:用跨度表示改进科学命名实体识别

SEPT: Improving Scientific Named Entity Recognition with Span Representation

Tan Yan, Heyan Huang, Xian-Ling Mao

摘要:

我们引入了一个新的科学命名实体识别器,称为SEPT,它代表Span Extractor with Pre-trained Transformers。在最近的论文中,跨度提取器已被证明是一个强大的模型相比,序列标记模型。然而,我们发现,随着预训练的语言模型的发展,跨度提取器的性能似乎变得与序列标记模型相似。为了保持跨度表示的优点,我们对模型进行了欠采样,以平衡正负样本,减少搜索空间。此外,我们简化了原始网络结构,将跨度提取器与BERT结合起来。实验表明,即使是简化的体系结构也能达到相同的性能,SEPT在不涉及关系信息的情况下也能实现科学的命名实体识别,达到了一个新的技术水平。

英文摘要:

We introduce a new scientific named entity recognizer called SEPT, which stands for Span Extractor with Pre-trained Transformers. In recent papers, span extractors have been demonstrated to be a powerful model compared with sequence labeling models. However, we discover that with the development of pre-trained language models, the performance of span extractors appears to become similar to sequence labeling models. To keep the advantages of span representation, we modified the model by under-sampling to balance the positive and negative samples and reduce the search space. Furthermore, we simplify the origin network architecture to combine the span extractor with BERT. Experiments demonstrate that even simplified architecture achieves the same performance and SEPT achieves a new state of the art result in scientific named entity recognition even without relation information involved.

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。

↑