We hypothesize that explicit integration of contextual information into an Multi-task Learning framework would emphasize the significance of context for boosting performance in jointly learning Named Entity Recognition (NER) and Relation Extraction (RE). Our work proves this hypothesis by segmenting entities from their surrounding context and by building contextual representations using each independent segment. This relation representation allows for a joint NER/RE system that achieves near state-of-the-art (SOTA) performance on both NER and RE tasks while beating the SOTA RE system at end-to-end NER & RE with a 49.07 F1.
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
Studio Ousia;RIKEN AIP(理化学研究所先进智能项目中心);University of Washington(华盛顿大学);Nara Institute of Science and Technology(奈良先端科学技术大学院大学);National Institute of Informatics(国立情报学研究所)
Learning to Infer Entities, Properties and their Relations from Clinical Conversations
Google Inc.(谷歌公司)
最近,我们提出了跨度属性标记(SAT)模型(Du等人,2019)来推断临床实体(例如,症状)及其性质(例如,持续时间)。它解决了大的标签空间和有限的训练数据的挑战,使用分层的两阶段的方法,确定感兴趣的跨度在标记步骤和分配标签的跨度在分类步骤。我们扩展了SAT模型,不仅可以共同推断实体及其属性,还可以推断它们之间的关系。大多数关系抽取模型限制在几个相邻句子内推断标记之间的关系,主要是为了避免高计算复杂性。相比之下,我们提出的R-SAT(R-SAT)模型计算效率高,可以推断整个对话中的关系,平均持续时间为10分钟。我们评估我们的模型上的语料库的临床对话。当给出实体时,R-SAT在识别症状及其属性之间的关系方面优于基线约32%(0.82 vs 0.62 F分数),在药物及其属性方面优于基线约50%(0.60 vs 0.41 F分数)。在联合推断实体和关系这一更困难的任务上,R-SAT模型在症状和药物方面的表现分别为0.34和0.45,显著优于基线模型的0.18和0.35。使用消融分析来量化模型的不同组件的贡献。
Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions
East China University of Science and Technology(华东理工大学);Shanghai Shuguang Hospital(上海曙光医院)
临床命名实体识别(Clinical Named Entity Recognition,CNER)的目的是对电子病历中的疾病、症状、治疗、检查、身体部位等临床术语进行识别和分类,是临床和翻译研究的基础和关键任务。近年来,深度学习方法在CNER任务中取得了重大成功。然而,这些方法在很大程度上依赖于递归神经网络(RNN),它保持了一个通过时间传播的隐藏激活向量,因此导致了太多的时间来训练模型。本文提出了一种基于条件随机场的残差扩张卷积神经网络(RD-CNN-CRF)来解决这一问题,首先将汉字和字典特征投影到稠密向量表示中,然后将其输入残差扩张卷积神经网络以捕获上下文特征。最后,采用条件随机场来捕获相邻标签之间的依赖性。CCKS-2017任务2基准数据集上的计算结果表明,我们提出的RD-CNN-CRF方法在计算性能和训练时间方面都与最先进的基于RNN的方法相媲美。
Terminologies augmented recurrent neural network model for clinical named entity recognition
Paris University(巴黎大学);AP-HP(巴黎公共援助医院);LIMSI(法国计算机科学与自动化研究所);CNRS(法国国家科学研究中心);Univ. Paris-Sud(巴黎南大学);Université Paris-Saclay(巴黎萨克雷大学);Sorbonne Université(索邦大学);Inserm(法国国家健康与医学研究院);Univ Paris 13(巴黎第十三大学);LIMICS(医学信息学与电子健康知识工程实验室)
我们的目的是提高性能的监督模型的临床命名实体识别(NER)使用医学术语。为了评估我们的系统在法国,我们建立了一个语料库的5种类型的临床实体。我们使用了一个基于术语的系统作为基线,建立在UMLS和SNOMED。然后,我们评估了一个biGRU-CRF,和一个混合系统使用的预测的术语为基础的系统的biGRU-CRF的功能。在英语中,我们在i2 b2 -2009药物名称识别的药物挑战赛上评估了NER系统,其中包含268个文档的8,573个实体。在法语中,我们建立了APcNER,这是一个包含147个文档的语料库,注释了5个实体(药物名称,体征或症状,疾病或病症,诊断程序或实验室测试和治疗程序)。我们评估每个NER系统使用精确和部分匹配定义的F-测度的NER。APcNER包含4,837个实体,需要28小时进行注释,注释者间一致性对于精确匹配的药物名称是可接受的(85%),对于非精确匹配的其他实体类型是可接受的(>70%)。对于i2 b2 -2009和APcNER上的药物名称识别,biGRU-CRF比基于术语的系统表现更好,精确匹配F测量值分别为91.1%和73%,81.9%和75%。此外,混合系统优于biGRU-CRF,精确匹配F测量值为92.2% vs 91.1%(i2 b2 -2009)和88.4% vs 81.9%(APcNER)。在APcNER语料库上,混合系统对5个实体的微平均F-测…
Learning the grammar of drug prescription: recurrent neural network grammars for medication information extraction in clinical texts
CHU Necker, AP-HP(巴黎公共医疗救助机构内克尔大学医院);INSERM UMR-S 872(法国国家健康与医学研究院 UMR-S 872);Sorbonne Paris Cité, Faculté de Médecine(索邦巴黎西岱大学医学院);Université de Paris(巴黎大学)
Named entity recognition architecture combining contextual and global features
University of Science and Technology in Hanoi(河内科技大学);University of La Rochelle(拉罗谢尔大学);Jozef Stefan Institute(约瑟夫·斯特凡研究所);University of Toulouse - IRIT(图卢兹大学 - 图卢兹信息研究所)
Leveraging deep active learning to identify low-resource mobility functioning information in public clinical notes
University of South Florida(南佛罗里达大学);Moffitt Cancer Center(莫菲特癌症中心);State University of New York at New Paltz(纽约州立大学新帕尔茨分校);Oklahoma State University(俄克拉荷马州立大学)
Enhancing Clinical Information Extraction with Transferred Contextual Embeddings
The Australian National University (ANU)(澳大利亚国立大学);Data61, Commonwealth Scientific and Industrial Research Organization (CSIRO)(澳大利亚联邦科学与工业研究组织Data61部门);University of Canberra(堪培拉大学);University of Turku(图尔库大学)
PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation
Korea Advanced Institute of Science and Technology(韩国科学技术院);Department of Neurology, Seoul National University Hospital(首尔国立大学医院神经科);Asan Medical Center, University of Ulsan, College of Medicine(釜山大学医学院阿桑医院);Haeundae Paik Hospital, Inje University(庆尚大学医院海undae医院)
Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework
The Ohio State University(俄亥俄州立大学);Translational Data Analytics Institute, The Ohio State University(俄亥俄州立大学转化数据分析研究所);College of Pharmacy, The Ohio State University(俄亥俄州立大学药学院)
Improving Extraction of Clinical Event Contextual Properties from Electronic Health Records: A Comparative Study
King’s College London(伦敦国王学院);Guy’s and St Thomas’ NHS Foundation Trust(盖伊和圣托马斯 NHS 基金会信托);King’s College Hospital NHS Foundation Trust(国王学院医院 NHS 基金会信托);University College London(伦敦大学学院);Health Data Research UK London(英国健康数据研究伦敦中心)
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
Intelligent Systems, Afeka Academic College of Engineering(阿法卡学术工程学院智能系统);School of Computer Science, Faculty of Sciences, Holon Institute of Technology(霍隆理工学院计算机科学学院)
An Emergency Medical Services Clinical Audit System driven by Named Entity Recognition from Deep Learning
Saw Swee Hock School of Public Health, National University of Singapore and National University Health System(苏瑞福公共卫生学院、新加坡国立大学及新加坡国立大学健康系统);Singapore Civil Defence Force(新加坡民防部队);National University Hospital(国立大学医院);Home Team Science & Technology Agency(Home Team科技局);Singapore General Hospital(新加坡中央医院)
Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset
Systematic Comparative Analysis of Large Pretrained Language Models on Contextualized Medication Event Extraction
Center of Excellence in Research and Education for Big Military Data Intelligence (CREDIT Center)(大数据智能卓越研究中心(CREDIT中心));Department of Electrical and Computer Engineering(电气与计算机工程系);Prairie View A&M University(普拉提维大学);Texas A&M University System(德克萨斯A&M大学系统)
Building a comprehensive syntactic and semantic corpus of Chinese clinical texts
School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);Ricoh Software Research Center (Beijing)(理光软件研究所(北京));School of Software, Harbin University of Science and Technology(哈尔滨理工大学软件学院);Medical Records Room, the Second Affiliated Hospital of Harbin Medical University(哈尔滨医科大学附属第二医院病案室)
University of Illinois at Chicago(伊利诺伊大学芝加哥分校);University at Buffalo(布法罗大学);Zhejiang Lab(之江实验室);Tencent Medical AI Lab(腾讯医疗AI实验室);Alibaba Group(阿里巴巴集团);Tencent America(腾讯美国)