Search Results for author: Hongying Zan

Found 10 papers, 1 papers with code

Chinese Grammatical Error Diagnosis Based on RoBERTa-BiLSTM-CRF Model

no code implementations AACL (NLP-TEA) 2020 Yingjie Han, Yingjie Yan, Yangchao Han, Rui Chao, Hongying Zan

Chinese Grammatical Error Diagnosis (CGED) is a natural language processing task for the NLPTEA6 workshop.

Konwledge-Enabled Diagnosis Assistant Based on Obstetric EMRs and Knowledge Graph

no code implementations CCL 2020 Kunli Zhang, Xu Zhao, Lei Zhuang, Qi Xie, Hongying Zan

In this paper, we treat the diagnosis assistant as a multi-label classification task and propose a Knowledge-Enabled Diagnosis Assistant (KEDA) model for the obstetric diagnosis assistant.

Disease Prediction Multi-Label Classification

Self-Supervised Curriculum Learning for Spelling Error Correction

no code implementations EMNLP 2021 Zifa Gan, Hongfei Xu, Hongying Zan

By contrast, Curriculum Learning (CL) utilizes training data differently during training and has shown its effectiveness in improving both performance and training efficiency in many other NLP tasks.

脑卒中疾病电子病历实体及实体关系标注语料库构建(Corpus Construction for Named-Entity and Entity Relations for Electronic Medical Records of Stroke Disease)

no code implementations CCL 2021 Hongyang Chang, Hongying Zan, Yutuan Ma, Kunli Zhang

“本文探讨了在脑卒中疾病中文电子病历文本中实体及实体间关系的标注问题, 提出了适用于脑卒中疾病电子病历文本的实体及实体关系标注体系和规范。在标注体系和规范的指导下, 进行了多轮的人工标注及校正工作, 完成了158万余字的脑卒中电子病历文本实体及实体关系的标注工作。构建了脑卒中电子病历实体及实体关系标注语料库(Stroke Electronic Medical Record entity and entity related Corpus SEMRC)。所构建的语料库共包含命名实体10594个, 实体关系14457个。实体名标注一致率达到85. 16%, 实体关系标注一致率达到94. 16%。”

糖尿病电子病历实体及关系标注语料库构建(Construction of Corpus for Entity and Relation Annotation of Diabetes Electronic Medical Records)

no code implementations CCL 2021 Yajuan Ye, Bin Hu, Kunli Zhang, Hongying Zan

“电子病历是医疗信息的重要来源, 包含大量与医疗相关的领域知识。本文从糖尿病电子病历文本入手, 在调研了国内外已有的电子病历语料库的基础上, 参考坉圲坂圲实体及关系分类, 建立了糖尿病电子病历实体及实体关系分类体系, 并制定了标注规范。利用实体及关系标注平台, 进行了实体及关系预标注及多轮人工校对工作, 形成了糖尿病电子病历实体及关系标注语料库(Diabetes Electronic Medical Record entity and Related Corpus DEMRC)。所构建的DEMRC包含8899个实体、456个实体修饰及16564个关系。对DEMRC进行一致性评价和分析, 标注结果达到了较高的一致性。针对实体识别和实体关系抽取任务, 分别采用基于迁移学习的Bi-LSTM-CRF模型和RoBERTa模型进行初步实验, 并对语料库中的各类实体及关系进行评估, 为后续糖尿病电子病历实体识别及关系抽取研究以及糖尿病知识图谱构建打下基础。”

融入篇章信息的文学作品命名实体识别(Document-level Literary Named Entity Recognition)

no code implementations CCL 2021 Yuxiang Jia, Rui Chao, Hongying Zan, Huayi Dou, Shuai Cao, Shuo Xu

“命名实体识别是文学作品智能分析的基础性工作, 当前文学领域命名实体识别的研究还较薄弱, 一个主要的原因是缺乏标注语料。本文从金庸小说入手, 对两部小说180余万字进行了命名实体的标注, 共标注4类实体5万多个。针对小说文本的特点, 本文提出融入篇章信息的命名实体识别模型, 引入篇章字典保存汉字的历史状态, 利用可信度计算融合BiGRU-CRF与Transformer模型。实验结果表明, 利用篇章信息有效地提升了命名实体识别的效果。最后, 我们还探讨了命名实体识别在小说社会网络构建中的应用。”

named-entity-recognition Named Entity Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.