检索结果-南通市图书馆

Improving link prediction models through a performance enhancement scheme:a study on semi-supervised learning and model soup

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2024年第4期31卷 43-53页

作者： Qi Donglin chen shudong Du Rong Yu Yong Tong Da Intelligent Manufacturing Electronics Research and Development Center Institute of Microelectronics of the Chinese Academy of SciencesBeijing 100029China School of Integrated Circuits University of Chinese Academy of SciencesBeijing 100049China

As an important method for knowledge graph(KG)complementation,link prediction has become a hot research topic in recent *** this paper,a performance enhancement scheme for link prediction models based on the idea of semi-supervised learning and model soup is proposed,which effectively improves the model performance on several mainstream link prediction models with small changes to their *** novel scheme consists of two main parts,one is predicting potential fact triples in the graph with semi-supervised learning strategies,the other is creatively combining semi-supervised learning and model soup to further improve the final model performance without adding significant computational *** validate the effectiveness of the scheme for a variety of link prediction models,especially on the dataset with dense *** terms of CompGCN,the model with the best overall performance among the tested models improves its Hits@1 metric by 14.7%on the FB15K-237 dataset and 7.8%on the WN18RR dataset after using the enhancement ***,it is observed that the semi-supervised learning strategy in the augmentation scheme has a significant improvement for multi-class link prediction models,and the performance improvement brought by the introduction of the model soup is related to the specific tested models,as the performances of some models are improved while others remain largely unaffected.

关键词： natural language processing knowledge graph(KG) link prediction model soup semi-supervised learning

同方期刊数据库

SHEL:a semantically enhanced hardware-friendly entity linking method

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2024年第1期30卷 13-22页

作者：亓东林 chen shudong DU Rong TONG Da YU Yong Institute of Microelectronics of Chinese Academy of Sciences Beijing 100029P.R.China University of Chinese Academy of Sciences Beijing 100190P.R.China

With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent ***,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this *** researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition *** paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good ***,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling *** series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this *** terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.

关键词： entity linking(EL) pre-trained models knowledge graph text summarization semantic enhancement

《临症指南医案》及《张聿青医案》治泻用药规律探析

在线全文

学校读者我要写书评

暂无评论

长春大学学报 2024年第2期34卷 35-39页

作者：艾民陈书栋长春大学特殊教育学院长春130022

对《临证指南医案》和《张聿青医案》两部医学著作中94例治疗泄泻的医案所用药物用药频次、归经、药味和药性进行统计分析,发现叶天士和张聿青两位医家在治疗泄泻时,常用健脾和胃、利水渗湿、疏肝理脾、温补肾阳等治法,所用药物归经多... 详细信息

对《临证指南医案》和《张聿青医案》两部医学著作中94例治疗泄泻的医案所用药物用药频次、归经、药味和药性进行统计分析,发现叶天士和张聿青两位医家在治疗泄泻时,常用健脾和胃、利水渗湿、疏肝理脾、温补肾阳等治法,所用药物归经多归脾、胃经,药味多偏辛、甘,药性多偏温、热,以求为中医临床治疗泄泻提供更多的方法和思路。

关键词：泄泻中医治疗临证指南医案

牛磺熊去氧胆酸干预缺糖缺氧条件下脊髓神经元的凋亡

在线全文

学校读者我要写书评

暂无评论

中国组织工程研究 2024年第4期28卷 528-534页

作者：陈泽鹏侯永辉陈树东侯宇林定坤广州中医药大学第二临床医学院广东省广州市510405 广州中医药大学岭南医学研究中心广东省广州市510405 广东省中医院骨一科广东省广州市510120

背景:牛磺熊去氧胆酸是一种亲水性胆汁酸衍生物,在多种神经系统疾病模型中均有神经保护作用,但目前鲜有报道研究牛磺熊去氧胆酸对脊髓损伤的作用。目的:观察缺糖缺氧条件下牛磺熊去氧胆酸对脊髓神经元凋亡的作用,以及对脊髓损伤后小鼠... 详细信息

背景:牛磺熊去氧胆酸是一种亲水性胆汁酸衍生物,在多种神经系统疾病模型中均有神经保护作用,但目前鲜有报道研究牛磺熊去氧胆酸对脊髓损伤的作用。目的:观察缺糖缺氧条件下牛磺熊去氧胆酸对脊髓神经元凋亡的作用,以及对脊髓损伤后小鼠运动功能恢复的影响。方法:①体外实验:从孕13.5 d的C57 BL/6小鼠胚胎中分离提取原代脊髓神经元,培养72 h后,分3组处理:正常组加入Neurobasal完全培养基,置于CO_(2)培养箱(体积分数5%CO_(2)+95%空气)内培养24 h;氧糖剥夺组加入无糖的Neurobasal培养基,置于三气培养箱(体积分数94%N2+5%CO_(2)+1%O_(2))培养12 h,更换为Neurobasal完全培养基后置于CO_(2)培养箱内培养12 h;实验组处理过程大致同氧糖剥夺组,其中在加入无糖Neurobasal培养基的同时加入牛磺熊去氧胆酸。采用TUNEL染色检测细胞凋亡,CCK-8法检测细胞活性,免疫荧光染色检测细胞βⅢ微管蛋白表达。②动物实验:采用随机数字表法将60只C57 BL/6小鼠分为假手术组、脊髓损伤组与实验组,每组20只,脊髓损伤组与实验组采用Allen打击法建立T_(9)-T_(10)脊髓损伤模型,造模后第1天开始,实验组灌胃给予牛磺熊去氧胆酸溶液,假手术组与脊髓损伤组灌胃给予生理盐水,1次/d。连续给药14 d后,采用行为学和组织学方法评估脊髓组织修复情况。结果与结论:①体外实验:TUNEL染色、CCK-8与免疫荧光染色检测显示,氧糖剥夺组细胞凋亡数量高于正常组(P<0.01),细胞活性与βⅢ微管蛋白表达低于正常组(P<0.01);实验组细胞凋亡数量低于氧糖剥夺组(P<0.01),细胞活性与βⅢ微管蛋白表达高于氧糖剥夺组(P<0.01)。②动物实验:旷场实验BBB评分与后肢足迹实验显示,实验组小鼠行走与运动功能恢复程度好于脊髓损伤组。苏木精-伊红染色显示,脊髓损伤组小鼠脊髓损伤部位可见明显畸形和空洞,神经细胞数量明显减少;与脊髓损伤组比较,实验组脊髓损伤病变面积显著减小,脊髓畸形程度更小、空洞更少,神经细胞数量增加。免疫荧光染色显示,脊髓损伤组神经元胞核标记神经元细胞数量少于假手术组(P<0.01),实验组神经元胞核标记神经元细胞数量高于脊髓损伤组(P<0.01)。③结果表明:牛磺熊去氧胆酸能减少缺糖缺氧引起的脊髓神经元凋亡、轴突的丢失,促进脊髓损伤小鼠运动功能的恢复。

关键词：牛磺熊去氧胆酸脊髓损伤缺糖缺氧脊髓神经元行为学细胞凋亡

Positive unlabeled named entity recognition with multi-granularity linguistic information

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2021年第4期27卷 373-380页

作者： Ouyang Xiaoye chen shudong Wang Rong Institute of Microelectronics Chinese Academy of SciencesBeijing 100029P.R.China University of Chinese Academy of Sciences Beijing 100049P.R.China Key Laboratory of Space Object Measurement Department Beijing Institute of Tracking and Telecommunications TechnologyBeijing 100094P.R.China

The research on named entity recognition for label-few domain is becoming increasingly *** this paper,a novel algorithm,positive unlabeled named entity recognition(PUNER)with multi-granularity language information,is proposed,which combines positive unlabeled(PU)learning and deep learning to obtain the multi-granularity language information from a few labeled in-stances and many unlabeled instances to recognize named ***,PUNER selects reliable negative instances from unlabeled datasets,uses positive instances and a corresponding number of negative instances to train the PU learning classifier,and iterates continuously to label all unlabeled ***,a neural network-based architecture to implement the PU learning classifier is used,and comprehensive text semantics through multi-granular language information are obtained,which helps the classifier correctly recognize named *** tests of the PUNER are carried out on three multilingual NER datasets,which are CoNLL2003,CoNLL 2002 and SIGHAN Bakeoff *** results demonstrate the effectiveness of the proposed PUNER.

关键词： named entity recognition(NER) deep learning neural network positive-unla-beled learning label-few domain multi-granularity(PU)

Joint learning based on multi-shaped filters for knowledge graph completion

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2021年第1期27卷 43-52页

作者： Li Shaojie chen shudong Ouyang Xiaoye Gong Lichen School of Microelectronics University of Chinese Academy of SciencesBeijing 100049P.R.China Institute of Microelectronics Chinese Academy of SciencesBeijing 100029P.R.China

To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple ***,these researches use only one single-shaped filter and fail to extract semantic features of different *** solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different *** shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple *** results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.

关键词： knowledge graph embedding(KGE) knowledge graph completion(KGC) convolutional neural network(CNN) joint learning multi-shaped filter

RotatS:temporal knowledge graph completion based on rotation and scaling in 3D space

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2023年第4期29卷 348-357页

作者：余泳 chen shudong TONG Da QI Donglin PENG Fei ZHAO Hua Institute of Microelectronics Chinese Academy of SciencesBeijing 100191P.R.China University of Chinese Academy of Sciences Beijing 100191P.R.China Beijing Institute of Tracking and Telecommunications Technology Beijing 100191P.R.China

As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks and deep question and answer(Q&A).Current research mainly fo-cuses on the completion of static knowledge graphs,and the temporal information in temporal knowl-edge graphs(TKGs)is ***,the temporal information is definitely very helpful for the *** that existing researches on temporal knowledge graph completion are difficult to process temporal information and to integrate entities,relations and time *** this work,a rotation and scaling(RotatS)model is proposed,which learns rotation and scaling transformations from head entity embedding to tail entity embedding in 3D spaces to capture the information of time and rela-tions in the temporal knowledge *** performance of the proposed RotatS model have been evaluated by comparison with several baselines under similar experimental conditions and space com-plexity on four typical knowl good graph completion datasets publicly available *** study shows that RotatS can achieve good results in terms of prediction accuracy.

关键词： knowledge graph(KG) temporal knowledge graph(TKG) knowledge graph com-pletion(KGC) rotation and scaling(RotatS)

Semantic-aware graph convolution network on multi-hop paths for link prediction

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2023年第3期29卷 269-278页

作者：彭斐 chen shudong QI Donglin YU Yong TONG Da Institute of Microelectronics of the Chinese Academy of Sciences Beijing 100029P.R.China University of Chinese Academy of Sciences Beijing 101408P.R.China

Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.

关键词： knowledge graph(KG) link prediction graph convolution network(GCN) knowledge graph completion(KGC) multi-hop paths semantic information

用于中药中农药残留检测的全自动快速样品处理仪验证与评价

在线全文

学校读者我要写书评

暂无评论

化学分析计量 2024年第10期33卷 99-104页

作者：陈树东梁金钊蒋超胡文军广东省中药研究所广东省药品监督管理局药品检验用国产仪器设备质量评价与应用重点实验室广州510640 仪学科技广州有限公司广州510320

采用中药农药残留的样品处理方法作为验证方式,建立了全自动快速样品处理(QuEChERS)设备的验证与评价方法。验证的设备按照标准方法的步骤执行样品处理过程,对影响最终实验结果的基本性能和应用效果进行验证。验证的农药化合物在0.005~0... 详细信息

采用中药农药残留的样品处理方法作为验证方式,建立了全自动快速样品处理(QuEChERS)设备的验证与评价方法。验证的设备按照标准方法的步骤执行样品处理过程,对影响最终实验结果的基本性能和应用效果进行验证。验证的农药化合物在0.005~0.25μg/mL质量浓度范围内与其相应的色谱峰面积具有较好的线性关系,相关系数均大于0.99,检出限均为0.002 mg/kg。中药样品在不同浓度的加标水平下的加标平均回收率为71.6%~128.8%,相对标准偏差为0.1%~8.1%。全自动快速样品处理设备实验操作的一致性程度较高,设备在分液、移液和加盐等步骤的操作可以满足实验的要求。采用自动化样品处理方式应用于中药农药残留检测,能有效减少人为误差,提高检测的准确性、重现性和溯源性,为分析仪器的自动化和智能化技术验证提供了技术支持。

关键词：设备验证设备评价农药残留中药全自动QuEChERS实验仪