Li Dongmei, Yang Yu, Cui Jinman, Meng Xianghao, Qu Jintao, Jiang Zhuobin, Zhao Yufeng
School of Information Science and Technology, Beijing Forestry University, 100083, Beijing, China.
Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, 100083, Beijing, China.
BMC Med Inform Decis Mak. 2024 Jul 31;24(1):218. doi: 10.1186/s12911-024-02577-1.
Most Chinese joint entity and relation extraction tasks in medicine involve numerous nested entities, overlapping relations, and other challenging extraction issues. In response to these problems, some traditional methods decompose the joint extraction task into multiple steps or multiple modules, resulting in local dependency in the meantime.
To alleviate this issue, we propose a joint extraction model of Chinese medical entities and relations based on RoBERTa and single-module global pointer, namely RSGP, which formulates joint extraction as a global pointer linking problem. Considering the uniqueness of Chinese language structure, we introduce the RoBERTa-wwm pre-trained language model at the encoding layer to obtain a better embedding representation. Then, we represent the input sentence as a third-order tensor and score each position in the tensor to prepare for the subsequent process of decoding the triples. In the end, we design a novel single-module global pointer decoding approach to alleviate the generation of redundant information. Specifically, we analyze the decoding process of single character entities individually, improving the time and space performance of RSGP to some extent.
In order to verify the effectiveness of our model in extracting Chinese medical entities and relations, we carry out the experiments on the public dataset, CMeIE. Experimental results show that RSGP performs significantly better on the joint extraction of Chinese medical entities and relations, and achieves state-of-the-art results compared with baseline models.
The proposed RSGP can effectively extract entities and relations from Chinese medical texts and help to realize the structure of Chinese medical texts, so as to provide high-quality data support for the construction of Chinese medical knowledge graphs.
大多数中文医学领域的联合实体与关系抽取任务涉及大量嵌套实体、重叠关系以及其他具有挑战性的抽取问题。针对这些问题，一些传统方法将联合抽取任务分解为多个步骤或多个模块，同时导致了局部依赖性。
为缓解这一问题，我们提出了一种基于RoBERTa和单模块全局指针的中文医学实体与关系联合抽取模型，即RSGP，它将联合抽取表述为一个全局指针链接问题。考虑到中文语言结构的独特性，我们在编码层引入RoBERTa-wwm预训练语言模型以获得更好的嵌入表示。然后，我们将输入句子表示为三阶张量并对张量中的每个位置进行评分，为后续三元组解码过程做准备。最后，我们设计了一种新颖的单模块全局指针解码方法来缓解冗余信息的产生。具体而言，我们分别分析单字符实体的解码过程，在一定程度上提高了RSGP的时间和空间性能。
为了验证我们的模型在抽取中文医学实体与关系方面的有效性，我们在公共数据集CMeIE上进行了实验。实验结果表明，RSGP在中文医学实体与关系的联合抽取上表现显著更好，与基线模型相比取得了最优结果。
所提出的RSGP能够有效地从中文医学文本中抽取实体与关系，有助于实现中文医学文本的结构化，从而为中文医学知识图谱的构建提供高质量的数据支持。
