中文电子病历实体识别任务的数据集以及相应数据集上系统模型性能表现。目前现存公开的中文电子病历标注数据十分稀缺，为了推动CNER系统在中文临床文本上的表现，中国知识图谱与语义计算大会(China Conference on Knowledge Graph and Semantic Computing, CCKS)在近几年都组织了面向中文电子病历的命名实体识别评测任务，下面我们主要关注CCKS CNER数据集上的结果。 一.CCKS 2017 CCKS17数据集：原始数据集分为训练集和测试集，其中训练集包括300个医疗记录，人工标注了五类实体(包括症状和体征、检查和检验、疾病和诊断、治疗、身体部位)。测试集包含100个医疗记录。

二.CCKS 2018 CCKS18数据集：原始数据集包括训练集和测试集。其中训练集包括600个医疗记录，人工标注了五类实体（包括解剖部位、症状描述、独立症状、药物、手术）。测试集包含400个医疗记录原始数据。

三.CCKS 2019 CCKS19数据集：原始数据集包括训练集和测试集。其中训练集包括1000个医疗记录，人工标注了六类实体（包括疾病和诊断、检查、检验、手术、药物、解剖部位）。测试集包含379个医疗记录原始数据。

四.CCKS 2020 CCKS20数据集：原始数据集包括训练集和测试集．其中训练集包括1050个医疗记录，人工标注了六类实体（包括疾病和诊断、检查、检验、手术、药物、解剖部位）。测试集未公开。

五.中文电子病历实体识别研究相关论文 在中文电子病历实体识别任务上，已经有不少研究方法被提出，这些研究主要集中在对领域特征的探索上，即在通用领域NER方法的基础上，研究中文汉字特征和电子病历知识特征等来提升模型性能。 1.综述论文 （1）CCKS 2019知识图谱评测技术报告：实体、关系、事件及问答.pdf: https://url39.ctfile.com/f/2501739-763779502-620aeb?p=2096 (访问密码: 2096) （2）Knowledge Graph and Semantic Computing_CCKS2019.pdf: https://url39.ctfile.com/f/2501739-763779548-4296e3?p=2096 (访问密码: 2096) （3）电子病历命名实体识别和实体关系抽取研究综述.pdf: https://url39.ctfile.com/f/2501739-763779552-0f8c05?p=2096 (访问密码: 2096) （4）中文电子病历的命名实体识别研究进展.pdf: https://url39.ctfile.com/f/2501739-763779568-c71029?p=2096 (访问密码: 2096)

2.方法论文 （1）A BERT-BiLSTM-CRF Model for Chinese Electronic Medical Records Named Entity Recognition.pdf: https://url39.ctfile.com/f/2501739-763779614-3a3e59?p=2096 (访问密码: 2096) （2）A Conditional Random Fields Approach to Clinical Name Entity Recognition.pdf: https://url39.ctfile.com/f/2501739-763779615-53b327?p=2096 (访问密码: 2096) （3）A hybrid approach for named entity recognition in Chinese electronic medical record.pdf: https://url39.ctfile.com/f/2501739-763779616-7f6214?p=2096 (访问密码: 2096) （4）A multitask bi-directional RNN model for named entity recognition on Chinese electronic medical records.pdf: https://url39.ctfile.com/f/2501739-763779632-f93922?p=2096 (访问密码: 2096) （5）Adversarial training based lattice LSTM for Chinese clinical named entity recognition.pdf: https://url39.ctfile.com/f/2501739-763779633-6388af?p=2096 (访问密码: 2096) （6）An attention-based deep learning model for clinical named entity recognition of Chinese electronic medical records.pdf: https://url39.ctfile.com/f/2501739-763779634-c6307f?p=2096 (访问密码: 2096) （7）Chinese Clinical Named Entity Recognition in Electronic Medical Records：Development of a Lattice Long Short-Term Memory Model With Contextualized Character Representations.pdf: https://url39.ctfile.com/f/2501739-763779650-f617ce?p=2096 (访问密码: 2096) （8）Chinese Clinical Named Entity Recognition Using Residual Dilated Convolutional Neural Network With Conditional Random Field.pdf: https://url39.ctfile.com/f/2501739-763779651-9c33e1?p=2096 (访问密码: 2096) （9）Chinese clinical named entity recognition with radical-level feature and selfattention mechanism.pdf: https://url39.ctfile.com/f/2501739-763779667-624fd5?p=2096 (访问密码: 2096) （10）Chinese clinical named entity recognition with variant neural structures based on BERT methods.pdf: https://url39.ctfile.com/f/2501739-763779668-062bee?p=2096 (访问密码: 2096) （11）Chinese Clinical Named Entity Recognition with Word-Level Information Incorporating Dictionaries.pdf: https://url39.ctfile.com/f/2501739-763779669-0428fe?p=2096 (访问密码: 2096) （12）Chinese medical named entity recognition based on multi-granularity semantic dictionary and multimodal tree.pdf: https://url39.ctfile.com/f/2501739-763779673-38b190?p=2096 (访问密码: 2096) （13）Clinical Named Entity Recognition From Chinese Electronic Health Records via Machine Learning Methods.pdf: https://url39.ctfile.com/f/2501739-763779689-b44960?p=2096 (访问密码: 2096) （14）Cross domains adversarial learning for Chinese named entity recognition for online medical consultation.pdf: https://url39.ctfile.com/f/2501739-763779693-9c8af4?p=2096 (访问密码: 2096) （15）DUTIR at the CCKS-2018 Task1：A Neural Network Ensemble Approach for Chinese Clinical Named Entity Recognition.pdf: https://url39.ctfile.com/f/2501739-763779694-b026b6?p=2096 (访问密码: 2096) （16）Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text.pdf: https://url39.ctfile.com/f/2501739-763779695-f65e62?p=2096 (访问密码: 2096) （17）HITSZ_CNER：A hybrid system for entity recognition from Chinese clinical text.pdf: https://url39.ctfile.com/f/2501739-763779699-dd242a?p=2096 (访问密码: 2096) （18）Incorporating dictionaries into deep neural networks for the Chinese clinical named entity recognition.pdf: https://url39.ctfile.com/f/2501739-763779715-8d9e12?p=2096 (访问密码: 2096) （19）Noisy Label Learning for Chinese Medical Named Entity Recognition Based on Uncertainty Strategy.pdf: https://url39.ctfile.com/f/2501739-763779716-90d51f?p=2096 (访问密码: 2096) （20）基于BERT与模型融合的医疗命名实体识别.pdf: https://url39.ctfile.com/f/2501739-763779717-c2ce34?p=2096 (访问密码: 2096) （21）基于BERT与字形字音特征的医疗命名实体识别.pdf: https://url39.ctfile.com/f/2501739-763779718-3f17ba?p=2096 (访问密码: 2096) （22）基于笔画ELMo和多任务学...文电子病历命名实体识别研究_罗凌.caj: https://url39.ctfile.com/f/2501739-763779734-d2642c?p=2096 (访问密码: 2096) （23）基于句子级Lattice长短记忆神经网络的中文电子病历命名实体识别.pdf: https://url39.ctfile.com/f/2501739-763779735-808387?p=2096 (访问密码: 2096) （24）融入语言模型和注意力机制的临床电子病历命名实体识别.pdf: https://url39.ctfile.com/f/2501739-763779751-62def3?p=2096 (访问密码: 2096)

参考文献： [1]中文电子病历实体识别现存方法性能：https://github.com/lingluodlut/Chinese-BioNLP/blob/main/CNER_sota.md