期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到189篇文章
< 1 2 … 10 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
An Efficient Way to Parse Logs Automatically for Multiline Events 认领 引用
1
作者 Mingguang Yu Xia Zhang 《Computer Systems Science & Engineering》 SCIE EI 2023年第9期2975-2994,共20页
In order to obtain information or discover knowledge from system logs,the first step is to performlog parsing,whereby unstructured raw logs can be transformed into a sequence of structured events.Although comprehensiv... In order to obtain information or discover knowledge from system logs,the first step is to performlog parsing,whereby unstructured raw logs can be transformed into a sequence of structured events.Although comprehensive studies on log parsing have been conducted in recent years,most assume that one event object corresponds to a single-line message.However,in a growing number of scenarios,one event object spans multiple lines in the log,for which parsing methods toward single-line events are not applicable.In order to address this problem,this paper proposes an automated log parsing method for multiline events(LPME).LPME finds multiline event objects via iterative scanning,driven by a set of heuristic rules derived from practice.The advantage of LPME is that it proposes a cohesion-based evaluation method for multiline events and a bottom-up search approach that eliminates the process of enumerating all combinations.We analyze the algorithmic complexity of LPME and validate it on four datasets from different backgrounds.Evaluations show that the actual time complexity of LPME parsing for multiline events is close to the constant time,which enables it to handle large-scale sample inputs.On the experimental datasets,the performance of LPME achieves 1.0 for recall,and the precision is generally higher than 0.9,which demonstrates the effectiveness of the proposed LPME. 展开更多
关键词 Log parsing log management log analysis system maintenance
暂未订购 下载PDF
Using SVM to construct a Chinese dependency parser 认领 引用 被引量：4
2
作者 许云 张锋 《Journal of Zhejiang University-SCIENCE A》 EI CAS 2006年第2期199-203,共5页
In Chinese, dependency analysis has been shown to be a powerful syntactic parser because the order of phrases in a sentence is relatively free compared with English. Conventional dependency parsers require a number of... In Chinese, dependency analysis has been shown to be a powerful syntactic parser because the order of phrases in a sentence is relatively free compared with English. Conventional dependency parsers require a number of sophisticated rules that have to be handcrafted by linguists, and are too cumbersome to maintain. To solve the problem, a parser using SVM (Support Vector Machine) is introduced. First, a new strategy of dependency analysis is proposed. Then some chosen feature types are used for learning and for creating the modification matrix using SVM. Finally, the dependency of phrases in the sentence is generated. Experiments conducted to analyze how each type of feature affects parsing accuracy, showed that the model can increase accuracy of the dependency parser by 9.2%. 展开更多
关键词 Syntactic parsing Dependency Support Vector Machine （SVM）
暂未订购 下载PDF
Linear algorithm for lexicographic enumeration of CFG parse trees 认领 引用 被引量：2
3
作者 DONG YunMei 《Science in China(Series F)》 2009年第7期1177-1202,共26页
We study CFG parse tree enumeration in this paper. By dividing the set of all parse trees into infinite hierarchies according to height of parse tree, the hierarchical lexicographic order on the set of parse trees is ... We study CFG parse tree enumeration in this paper. By dividing the set of all parse trees into infinite hierarchies according to height of parse tree, the hierarchical lexicographic order on the set of parse trees is established. Then grammar-based algorithms for counting and enumerating CFG parse trees in this order are presented. To generate a parse tree of height n, the time complexity is O（n）. If τ is a lowest parse tree for its yield, then O（n） =O（｜｜τ｜｜ ＋ 1）, where ｜｜τ｜｜ is the length of the sentence （yield） generated by τ. The sentence can be obtained as a by-product of the parse tree. To compute sentence from its parse tree （needn＇t be lowest one）, the time complexity is O（node）＋O（｜｜τ｜｜ ＋ 1）, where node is the number of non-leaf nodes of parse tree τ. To generate both a complete lowest parse tree and its yield at the same time, the time complexity is O（｜｜τ｜｜ ＋ 1）. 展开更多
关键词 hierarchical construction of set of parse trees lexicographic enumeration of parse trees counting of parse trees
Kernel-Based Semantic Relation Detection and Classification via Enriched Parse Tree Structure 认领 引用 被引量：9
4
作者 周国栋 朱巧明 《Journal of Computer Science & Technology》 SCIE EI CSCD 2011年第1期45-56,共12页
This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree ke... This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones. 展开更多
关键词 semantic relation detection and classification convolution tree kernel approximate matching context sensitiveness enriched parse tree structure
暂未订购 下载PDF
Neural Parse Combination 认领 引用 被引量：1
5
作者 Lin-Er Yang Mao-Song Sun +4 位作者 Yong Cheng Jia-Cheng Zhang Zheng-Hao Liu Huan-Bo Luan Yang Liu 《Journal of Computer Science & Technology》 SCIE EI CSCD 2017年第4期749-757,共9页
Analyzing the syntactic structure of natural languages by parsing is an important task in artificial intelligence. Due to the complexity of natural languages, individual parsers tend to make different yet complementar... Analyzing the syntactic structure of natural languages by parsing is an important task in artificial intelligence. Due to the complexity of natural languages, individual parsers tend to make different yet complementary errors. We propose a neural network based approach to combine parses from different parsers to yield a more accurate parse than individual ones. Unlike conventional approaches, our method directly transforms linearized candidate parses into the ground-truth parse. Experiments on the Penn English Treebank show that the proposed method improves over a state-of-the-art parser combination approach significantly. 展开更多
关键词 neural network parsing parse combination
暂未订购 下载PDF
Semantic Role Labeling of Chinese Nominal Predicates with Dependency-Driven Constituent Parse Tree Structure 认领 引用 被引量：2
6
作者 Hong-Ling Wang Guo-Dong Zhou 《Journal of Computer Science & Technology》 SCIE EI CSCD 2013年第6期1117-1126,共10页
This paper explores a tree kernel based method for semantic role labeling(SRL)of Chinese nominal predicates via a convolution tree kernel.In particular,a new parse tree representation structure,called dependency-drive... This paper explores a tree kernel based method for semantic role labeling(SRL)of Chinese nominal predicates via a convolution tree kernel.In particular,a new parse tree representation structure,called dependency-driven constituent parse tree(D-CPT),is proposed to combine the advantages of both constituent and dependence parse trees.This is achieved by directly representing various kinds of dependency relations in a CPT-style structure,which employs dependency relation types instead of phrase labels in CPT(Constituent Parse Tree).In this way,D-CPT not only keeps the dependency relationship information in the dependency parse tree(DPT)structure but also retains the basic hierarchical structure of CPT style.Moreover,several schemes are designed to extract various kinds of necessary information,such as the shortest path between the nominal predicate and the argument candidate,the support verb of the nominal predicate and the head argument modified by the argument candidate,from D-CPT.This largely reduces the noisy information inherent in D-CPT.Finally,a convolution tree kernel is employed to compute the similarity between two parse trees.Besides,we also implement a feature-based method based on D-CPT.Evaluation on Chinese NomBank corpus shows that our tree kernel based method on D-CPT performs significantly better than other tree kernel-based ones and achieves comparable performance with the state-of-the-art feature-based ones.This indicates the effectiveness of the novel D-CPT structure in representing various kinds of dependency relations in a CPT-style structure and our tree kernel based method in exploring the novel D-CPT structure.This also illustrates that the kernel-based methods are competitive and they are complementary with the feature-based methods on SRL. 展开更多
关键词 semantic role labeling Chinese nominal predicate dependency-driven constituent parse tree tree kernel
暂未订购 下载PDF
Association of serum and vitreous homocysteine and uric acid concentrations with post-vitrectomy prognosis in patients with proliferative diabetic retinopathy 认领 引用
7
作者 Qi-Bo Ran Chun-Yan Lei +3 位作者 Sheng Gao Xiang-Gang Yang Fei-Peng Jiang Mei-Xia Zhang 《World Journal of Diabetes》 SCIE 2026年第1期107-120,共14页
BACKGROUND Proliferative diabetic retinopathy(PDR)is a major cause of vision loss,often requiring pars plana vitrectomy(PPV).Systemic and intraocular metabolic alterations,including dysregulation of homocysteine(Hcy)a... BACKGROUND Proliferative diabetic retinopathy(PDR)is a major cause of vision loss,often requiring pars plana vitrectomy(PPV).Systemic and intraocular metabolic alterations,including dysregulation of homocysteine(Hcy)and uric acid(UA),may influence surgical outcomes.While prior studies suggest associations between these biomarkers and retinal pathology,the role of these biomarkers in postoperative prognosis remains unclear.This study hypothesized that elevated serum and vitreous Hcy and UA levels are associated with visual,structural,and microvascular changes following PPV in patients with PDR.AIM To evaluate the associations between serum and vitreous Hcy/UA concentrations with postoperative outcomes in patients with PDR following PPV.METHODS In this prospective observational study at a tertiary care center,44 patients with PDR and 46 non-diabetic controls undergoing PPV between June 2021 and December 2022 were enrolled.Serum and vitreous Hcy and UA levels were measured.Best-corrected visual acuity,multimodal retinal imaging,and capillary density metrics were evaluated preoperatively and postoperatively.Correlation analyses assessed the relationships between biomarkers and clinical outcomes.RESULTS Patients with PDR showed significantly higher serum and vitreous Hcy and UA concentrations compared to those of controls.Serum Hcy and UA levels correlated with vitreous levels.In patients with PDR,elevated vitreous Hcy correlated with worse best-corrected visual acuity at 1 day and reduced peripapillary retinal nerve fiber layer thickness at 7 days and 90 days.It also correlated with foveal avascular zone enlargement at 90 days and inferior superficial capillary plexus(SCP)width density at 7 days.Vitreous UA had negative correlations at 30 days with nasal SCP length density and temporal/inner ring SCP width density.CONCLUSION Vitreous,but not serum,Hcy predicts post-PPV impairment,underscoring the prognostic value of the local ocular environment over systemic factors in PDR. 展开更多
关键词 Proliferative diabetic retinopathy Homocysteine Uric acid Pars plana vitrectomy Prognosis Optical coherence tomography Optical coherence tomography angiography Diabetic retinopathy
暂未订购 下载PDF
Explainable Anomaly Detection for System Logs in Distributed Environments 认领 引用
8
作者 Zhaojun Gu Wenlong Yue Chunbo Liu 《Computers, Materials & Continua》 SCIE EI 2026年第6期2272-2296,共25页
Anomaly detection in system logs is a critical technical means for identifying potential faults and security risks.In distributed environments,traditional deep learning-based log anomaly detection methods often suffer... Anomaly detection in system logs is a critical technical means for identifying potential faults and security risks.In distributed environments,traditional deep learning-based log anomaly detection methods often suffer from shortcomings in transparency,computational overhead,and data privacy protection.To address these issues,this paper proposes a federated learning-driven lightweight and explainable log anomaly detection framework named FedXLog.The framework adapts to heterogeneous logs through hierarchical feature extraction,introduces the Federated Gradient Trajectory Aggregation algorithm(FedGradTrace)to enhance the explainability of the parameter aggregation process,constructs lightweight models using knowledge distillation,and achieves globally consistent explanatory capabilities by integrating hash feature alignment.Experimental results demonstrate that FedXLog possesses the dual advantages of high detection accuracy and lightweight deployment for heterogeneous logs in distributed scenarios.It can effectively identify key decision-making features and locate typical root causes of anomalies.Notably,the framework has been specifically optimized for the unique characteristics of distributed logs.Distinguished from general federated explainable methods,it can directly support abnormal root cause localization in Operations and Maintenance scenarios.This further verifies the application value of scenario-specific adaptation of federated learning in the field of log analysis,thereby expanding the scope of application of explainable log anomaly detection. 展开更多
关键词 Anomaly detection log parsing federated learning explainable artificial intelligence
暂未订购 下载PDF
Oligodendrocyte precursor cells in the substantia nigra:Implications for Parkinson’s disease 认领 引用
9
作者 Julia C.Fitzgerald Friederike Pfeiffer 《Neural Regeneration Research》 SCIE CAS CSCD 2026年第8期3551-3552,共2页
Current evidence for oligodendrocyte precursor cell involvement in Parkinson’s disease:Oligodendroglial cells comprise a large cell population in the substantia nigra(SN).We recently reported a stable portion of olig... Current evidence for oligodendrocyte precursor cell involvement in Parkinson’s disease:Oligodendroglial cells comprise a large cell population in the substantia nigra(SN).We recently reported a stable portion of oligodendrocyte precursor cells(OPCs)in the SN pars compacta(SNpc)in a 1:1 ratio with dopaminergic neurons:15%of cells in neonate and young mice,rising to 20%in aged mice.Moreover,this portion represents only 45%of all oligodendroglial cells in the SNpc and 54%of all oligodendroglial cells in the SN pars reticulata(SNpr)(Fitzgerald et al.,2025).The SN is a deeply located area of the midbrain and the site of dopaminergic degeneration in Parkinson’s disease(PD).Recent advancement of single-cell transcriptomics revealed the involvement of non-neuronal cells in PD,with PD risk variants being strongly associated with oligodendroglia(reviewed by Salazar Campos et al.,2025). 展开更多
关键词 oligodendrocyte precursor cell oligodendrocyte precursor cells opcs substantia nigra sn we pars compacta snpc Parkinson's disease dopaminergic neurons oligodendroglial cells substantia nigra
暂未订购 下载PDF
Motor cortex in levodopa-induced dyskinesia:Systems and molecular changes after sub-anesthetic ketamine treatment 认领 引用
10
作者 Torsten Falk Stephen L.Cowen 《Neural Regeneration Research》 SCIE CAS CSCD 2026年第8期3533-3534,共2页
The loss of control over movement is one of the most devastating consequences of Parkinson’s disease(PD).The loss of control largely results from the gradual but inexorable destruction of dopamine-producing neurons i... The loss of control over movement is one of the most devastating consequences of Parkinson’s disease(PD).The loss of control largely results from the gradual but inexorable destruction of dopamine-producing neurons in the substantia nigra pars compacta.As dopamine levels fall,the ability to initiate,control,learn,and sustain actions declines.Treatment with the dopamine precursor levodopa can partly overcome motor impairments;however,years of use often leads to levodopa-induced dyskinesia(LID),a debilitating condition characterized by uncontrolled writhing and ballistic movements,making continued treatment difficult or impossible.While progress has been made towards unraveling the molecular and cellular processes driving the development of LID,far less is known about the changes in ongoing neuronal activity that contribute to LID expression. 展开更多
关键词 levodopa induced dyskinesia motor cortex molecular changes parkinson's disease pd substantia nigra pars compactaas sub anesthetic ketamine treatment Parkinsons disease dopamine precursor
暂未订购 下载PDF
Visual and anatomic outcomes of epiretinal membrane surgery in highly myopic eyes with varying axial lengths 认领 引用
11
作者 Xiao-Han Yang Xiao Feng +3 位作者 Bi-Ying Qi Xi-Jin Wu Qin-Lang Jia Wu Liu 《International Journal of Ophthalmology(English edition)》 SCIE CAS 2026年第6期1117-1123,共7页
AIM:To observe the clinical features and the surgical outcomes of the high myopic(HM)patients with epiretinal membranes(ERM).METHODS:This was a retrospective study enrolled HM patients diagnosed with ERM who underwent... AIM:To observe the clinical features and the surgical outcomes of the high myopic(HM)patients with epiretinal membranes(ERM).METHODS:This was a retrospective study enrolled HM patients diagnosed with ERM who underwent vitrectomy between May 2012 and November 2021.Three groups were divided according to axial length(AXL):26–<28 mm(n=43),28–<30 mm(n=22),and≥30 mm(n=11).Baseline characteristics and postoperative visual and anatomical outcomes were analyzed.RESULTS:Totally 76 consecutive eyes of 73 HM patients(27 males),with a mean age of 60.5±9.2y(range:38–84y)were enrolled.The initial best-corrected visual acuity(BCVA)of the three groups was not significantly different(P=0.498).Longer AXL was associated with a higher incidence of both inner and outer macular retinoschisis(MRS),ellipsoid zone(EZ)disruption,and foveal retinal detachment(all P<0.05).Only the eyes in the 26–<28 mm group showed a significant improvement in postoperative BCVA.BCVA was improved in 77.6%of the eyes.Among the eyes with BCVA not improved,58.8%belonged to the group 26–<28 mm.The postoperative macular hole was seen in 1(1.32%)eye.Multivariate linear regression analysis indicated that initial BCVA(P<0.001)and epiretinal proliferation(P=0.010)influenced the final BCVA.CONCLUSION:AXL is not significantly associated with visual recovery.Early operative intervention might have better visual and anatomical outcomes in HM-ERM patients. 展开更多
关键词 high myopia epiretinal membrane axial length pars plana vitrectomy visual acuity
暂未订购 下载PDF
A Multi-Branch Transformer-Enhanced Neural Framework for Joint Morphological Representation Learning 认领 引用
12
作者 Laura Baitenova Gulnar Mukhamejanova +2 位作者 Gauhar Munaitbas Saken Mambetov Zhanna Mukanova 《Computers, Materials & Continua》 SCIE EI 2026年第9期1516-1540,共25页
Morphological parsing is a fundamental task in natural language processing,particularly for morphologically rich languages where words encode complex grammatical and semantic information.This paper proposes a multi-br... Morphological parsing is a fundamental task in natural language processing,particularly for morphologically rich languages where words encode complex grammatical and semantic information.This paper proposes a multi-branch Transformer-enhanced neural framework for joint morphological representation learning,designed to improve segmentation and classification accuracy by integrating complementary feature extraction mechanisms.The proposed architecture combines convolutional layers for capturing local morphological patterns,recurrent layers for modeling sequential dependencies,and Transformer-based self-attention for learning global contextual relationships.This hybrid design enables the model to generate robust and context-aware representations that enhance morphological understanding.The framework is trained using morphologically annotated datasets and evaluated using standard performance metrics,including F1-score and classification accuracy.Experimental results demonstrate that the proposed model significantly outperforms conventional and single-architecture baselines in both segmentation and morphological classification tasks.The learned representations exhibit strong discriminative capability,allowing accurate identification of morpheme boundaries and grammatical features.Furthermore,the model demonstrates stable convergence behavior and strong generalization performance across diverse linguistic conditions.These findings confirm the effectiveness of integrating multi-level contextual and structural feature extraction mechanisms,establishing the proposed framework as a robust and scalable solution for advanced morphological parsing and representation learning in modern natural language processing applications. 展开更多
关键词 Morphological parsing transformer architecture multi-branch neural networks morphological segmentation contextual representation learning natural language processing morphological classification deep learning self-attention mechanism
暂未订购 下载PDF
Syntactic and Socially Responsible Machine Translation:A POS and DEP Integrated Framework for English–Tamil 认领 引用
13
作者 Rama Sugavanam Mythili Ramu 《Computers, Materials & Continua》 SCIE EI 2026年第4期2302-2326,共25页
When performing English-to-Tamil Neural Machine Translation(NMT),end users face several challenges due to Tamil's rich morphology,free word order,and limited annotated corpora.Although available transformer-based ... When performing English-to-Tamil Neural Machine Translation(NMT),end users face several challenges due to Tamil's rich morphology,free word order,and limited annotated corpora.Although available transformer-based models offer strong baselines,they compromise syntactic awareness and the detection and man-agement of offensive content in cluttered,noisy,and informal text.In this paper,we present POSDEP-Offense-Trans,a multi-task NMT framework that combines Part-of-Speech(POS)and Dependency Parsing(DEP)methods with a robust offensive language classification module.Our architecture enriches the Transformer encoder with syntax-aware embeddings and provides syntax-guided attention mechanisms.The architecture incorporates a structure-aware contrastive loss that reinforces syntactic consistency and deploys auxiliary classification heads for POS tagging,dependency parsing,and multi-class offensive detection.The classifier for offensive words operates at both sentence and token levels and obtains guidance from syntactic features and formal finite automata rules that model offensive language structures-hate speech,profanity,sarcasm,and threats.Using this architecture,we construct a syntactically enriched,socially annotated corpus.Experimental results show improvements in translation quality,with a BLEU score of 33.5,UAS/LAS parsing accuracies of 92.4%and 90%,and a 4.5%Fl-score gain in offensive content detection compared with baseline POS+DEP+Offense models.Also,the proposed model achieved 92.3%in offensive content neutralization,as confirmed by ablation studies.This comprehensive English-Tamil NMT model that unifies syntactic modelling and ethical filtering-laying the groundwork for applications in social media moderation,hate speech mitigation,and policy-compliant multilingual content generation. 展开更多
关键词 POS-awareNMT dependency parsing syntax-guided attention multi-task learning o.ensive language detection o.ensive language neutralization English–Tamil neural machine translation
暂未订购 下载PDF
A multi-dimensional automated framework for student code evaluation 认领 引用
14
作者 Xuran Tang Xudong Lu +4 位作者 Quanshun Yang Wei Guo Lizhen Cui Zhongmin Yan Peng Pan 《计算机教育》 2026年第6期322-329,共8页
With the rapid growth of big data technologies,data analysis skills have become essential across industries.Programming skills are increasingly important.Universities are adding programming courses to their core curri... With the rapid growth of big data technologies,data analysis skills have become essential across industries.Programming skills are increasingly important.Universities are adding programming courses to their core curricula.It is challenging to evaluate students'code assignments in a scientific and efficient way.Traditional test-case evaluation only checks functional correctness.However,it cannot assess code structure,logical rigor,or performance.To address this,our study builds a multi-dimensional automated framework.The framework evaluates student code from four angles:structure analysis,grammar analysis,time complexity analysis,and code similarity analysis.Notably,in code similarity analysis,the framework integrates structural features,with semantic analysis powered by large language models.Teachers can use the evaluation results to fully understand students'progress and dynamically adjust teaching content. 展开更多
关键词 Code parsing Abstract syntax tree Control flow graph Multi-dimensional evaluation
暂未订购 下载PDF
Surgical management of acute choroidal neovascularization related submacular hemorrhage:Three case reports 认领 引用
15
作者 Georges El Mollayess Mahmoud Jaroudi +2 位作者 Yehya Tlaiss Rayan Itaoui Bachir Abiad 《World Journal of Clinical Cases》 2026年第6期77-85,共9页
BACKGROUND Acute submacular hemorrhage(SMH)secondary to choroidal neovascularization(CNV),most commonly in neovascular age-related macular degeneration,is a vision-threatening emergency.Thick,fovea-involving SMH can c... BACKGROUND Acute submacular hemorrhage(SMH)secondary to choroidal neovascularization(CNV),most commonly in neovascular age-related macular degeneration,is a vision-threatening emergency.Thick,fovea-involving SMH can cause rapid photoreceptor injury,and timely intervention aimed at clot lysis and displacement,while continuing CNV suppression with anti-vascular endothelial growth factor(anti-VEGF)therapy,may improve anatomic outcomes.CASE SUMMARY We report a retrospective case series of three eyes with acute,fovea-involving CNV-related SMH treated with pars plana vitrectomy(PPV),subretinal tissue plasminogen activator(tPA),and expansile gas tamponade,with intravitreal anti-VEGF administered at the end of the procedure and continued postoperatively.Two cases had early intraocular pressure-related events(transient hypotony in one patient and transient ocular hypertension in another)requiring close postoperative monitoring and medical management.Follow-up color fundus photography and optical coherence tomography documented postoperative evolution of the hemorrhage compared with baseline,with ongoing anti-VEGF therapy planned to control the underlying CNV.CONCLUSION PPV with subretinal tPA and gas tamponade is a practical surgical strategy for acute,thick,fovea-involving SMH secondary to CNV,particularly when rapid displacement is desired.Careful documentation of operative parameters,strict postoperative monitoring for pressure-related complications,and continued anti-VEGF therapy are essential components of care. 展开更多
关键词 Submacular hemorrhage Choroidal neovascularization Alteplase Tissue plasminogen activator Pars plana vitrectomy Anti-vascular endothelial growth factor Neovascular age-related macular degeneration Case report
暂未订购 下载PDF
Enhancing Geometric Diagram Parsing with Deep Textual Semantics 认领 引用
16
作者 Xuhui Zhang Yanli Wang +1 位作者 Pengpeng Jian Lei Wu 《教育技术与创新》 2026年第2期1-9,共9页
A complete analysis of a geometric diagram hinges on interpreting both its fundamental primitives and the accompanying natural language text,yet existing models struggle to process the rich semantics within these desc... A complete analysis of a geometric diagram hinges on interpreting both its fundamental primitives and the accompanying natural language text,yet existing models struggle to process the rich semantics within these descriptions,often leading to ambiguity and restricted reasoning.To address this,our work introduces a method that deeply integrates a Transformer-based text encoder within a sophisticated visual parsing architecture.Central to our approach is a novel Semantic-Guided Cross-Attention mechanism,which uses a global sentence representation as a semantic query to dynamically guide the model’s focus toward the most relevant visual primitives based on the textual context.This end-to-end process generates context-aware visual features that are then processed by a Graph Neural Network(GNN)to perform robust cross-modal reasoning.Validated on the large-scale PGDP5K and IMP-Geometry3K datasets,our method demonstrates substantial accuracy improvements in relationship parsing and geometric proposition generation,especially in challenging cases involving text-diagram ambiguity,and significantly surpasses current state-of-the-art baselines by offering a more effective framework for fusing deep textual semantics with visual information. 展开更多
关键词 geometric problem solving multimodal learning geometric diagram parsing cross-attention DistilBERT
暂未订购 下载PDF
ML-Parser:An Eficient and Accurate Online Log Parser 认领 引用 被引量：2
17
作者 Yu-Qian Zhu Jia-Ying Deng +3 位作者 Jia-Chen Pu Peng Wang Shen Liang Wei Wang 《Journal of Computer Science & Technology》 SCIE EI CSCD 2022年第6期1412-1426,共15页
A log is a text message that is generated in various services,frameworks,and programs.The majority of log data mining tasks rely on log parsing as the first step,which transforms raw logs into formatted log templates.... A log is a text message that is generated in various services,frameworks,and programs.The majority of log data mining tasks rely on log parsing as the first step,which transforms raw logs into formatted log templates.Existing log parsing approaches often fail to effectively handle the trade-off between parsing quality and performance.In view of this,in this paper,we present Multi-Layer Parser(ML-Parser),an online log parser that runs in a streaming manner.Specifically,we present a multi-layer structure in log parsing to strike a balance between efficiency and effectiveness.Coarse-grained tokenization and a fast similarity measure are applied for efficiency while fine-grained tokenization and an accurate similarity measure are used for effectiveness.In experiments,we compare ML-Parser with two existing online log parsing approaches,Drain and Spell,on ten real-world datasets,five labeled and five unlabeled.On the five labeled datasets,we use the proportion of correctly parsed logs to measure the accuracy,and ML-Parser achieves the highest accuracy on four datasets.On the whole ten datasets,we use Loss metric to measure the parsing quality.ML-Parse achieves the highest quality on seven out of the ten datasets while maintaining relatively high efficiency. 展开更多
关键词 log parsing online approach structure extraction similarity measure
暂未订购 下载PDF
Chinese relation extraction for constructing satellite frequency and orbit knowledge graph:A survey 认领 引用 被引量：1
18
作者 Yuanzhi He Zhiqiang Li Zheng Dou 《Digital Communications and Networks》 SCIE EI CSCD 2025年第5期1305-1317,共13页
As Satellite Frequency and Orbit(SFO)constitute scarce natural resources,constructing a Satellite Frequency and Orbit Knowledge Graph(SFO-KG)becomes crucial for optimizing their utilization.In the process of building ... As Satellite Frequency and Orbit(SFO)constitute scarce natural resources,constructing a Satellite Frequency and Orbit Knowledge Graph(SFO-KG)becomes crucial for optimizing their utilization.In the process of building the SFO-KG from Chinese unstructured data,extracting Chinese entity relations is the fundamental step.Although Relation Extraction(RE)methods in the English field have been extensively studied and developed earlier than their Chinese counterparts,their direct application to Chinese texts faces significant challenges due to linguistic distinctions such as unique grammar,pictographic characters,and prevalent polysemy.The absence of comprehensive reviews on Chinese RE research progress necessitates a systematic investigation.A thorough review of Chinese RE has been conducted from four methodological approaches:pipeline RE,joint entityrelation extraction,open domain RE,and multimodal RE techniques.In addition,we further analyze the essential research infrastructure,including specialized datasets,evaluation benchmarks,and competitions within Chinese RE research.Finally,the current research challenges and development trends in the field of Chinese RE were summarized and analyzed from the perspectives of ecological construction methods for datasets,open domain RE,N-ary RE,and RE based on large language models.This comprehensive review aims to facilitate SFO-KG construction and its practical applications in SFO resource management. 展开更多
关键词 Relation extraction Information extraction Distant supervision Parsing tree Joint entity-relation extraction
暂未订购 下载PDF
KD-SegNet: Efficient Semantic Segmentation Network with Knowledge Distillation Based on Monocular Camera 认领 引用 被引量：1
19
作者 Thai-Viet Dang Nhu-Nghia Bui Phan Xuan Tan 《Computers, Materials & Continua》 SCIE EI 2025年第2期2001-2026,共26页
Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training per... Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training performance, the ability to effectively exploit the dataset, and the ability to adapt to complex environments when deploying the model. By utilizing the knowledge distillation techniques, the article strives to overcome the above challenges with the inheritance of the advantages of both the teacher model and the student model. More precisely, the ResNet152-PSP-Net model’s characteristics are utilized to train the ResNet18-PSP-Net model. Pyramid pooling blocks are utilized to decode multi-scale feature maps, creating a complete semantic map inference. The student model not only preserves the strong segmentation performance from the teacher model but also improves the inference speed of the prediction results. The proposed method exhibits a clear advantage over conventional convolutional neural network (CNN) models, as evident from the conducted experiments. Furthermore, the proposed model also shows remarkable improvement in processing speed when compared with light-weight models such as MobileNetV2 and EfficientNet based on latency and throughput parameters. The proposed KD-SegNet model obtains an accuracy of 96.3% and a mIoU (mean Intersection over Union) of 77%, outperforming the performance of existing models by more than 15% on the same training dataset. The suggested method has an average training time that is only 0.51 times less than same field models, while still achieving comparable segmentation performance. Hence, the semantic segmentation frames are collected, forming the motion trajectory for the system in the environment. Overall, this architecture shows great promise for the development of knowledge-based systems for MR’s navigation. 展开更多
关键词 Mobile robot navigation semantic segmentation knowledge distillation pyramid scene parsing fully convolutional networks
暂未订购 下载PDF
Risk prediction model for cataract after vitrectomy surgery:a 2-year study on primary rhegmatogenous retinal detachment 认领 引用
20
作者 Di Gong Da-Hui Ma +3 位作者 Qing Zhang Kuan-Rong Dang Wei-Hua Yang Jian-Tao Wang 《International Journal of Ophthalmology(English edition)》 SCIE CAS 2025年第11期2106-2115,共10页
AIM:To establish a risk prediction model for secondary cataract within 2y after pars plana vitrectomy(PPV)in patients with primary rhegmatogenous retinal detachment(RRD).METHODS:Clinical data of patients with primary ... AIM:To establish a risk prediction model for secondary cataract within 2y after pars plana vitrectomy(PPV)in patients with primary rhegmatogenous retinal detachment(RRD).METHODS:Clinical data of patients with primary RRD treated at the Shenzhen Eye Hospital were retrospectively collected.Twenty-four potential influencing factors,including patient characteristics and surgical factors,were selected for analysis.Independent risk factors for secondary cataract were identified through univariate comparisons and multivariate logistic regression analysis.A risk prediction model was constructed and evaluated using receiver operating characteristic(ROC)curves,area under the ROC curve(AUC),calibration plots,and decision curve analysis(DCA)curves.RESULTS:The 386 cases(389 eyes)of patients who underwent PPV and had complete surgical records were ultimately included.Within a 2-year longitudinal observation,41.39%of patients developed cataract secondary to PPV.Logistic regression results identified a history of hypertension[odds ratio(OR)=1.78,95%CI:1.002–3.163,P=0.049],silicone oil tamponade(OR=3.667,95%CI:2.373–5.667,P=0.000),and lens thickness(OR=1.978,95%CI:1.129–3.464,P=0.017)as independent risk factors for cataract secondary to PPV.The constructed nomogram achieved AUC=0.6974.Calibration plots indicated good agreement between predicted and observed outcomes,while DCA curves demonstrated the model’s clinical utility.CONCLUSION:By incorporating a history of hypertension,vitreous substitute type,and lens thickness,this study constructs a prediction model with moderate discriminative ability.This model offers a valuable tool for clinicians to identify high-risk patients early,potentially allowing for more timely interventions and improved patient outcomes. 展开更多
关键词 rhegmatogenous retinal detachment pars plana vitrectomy cataract prediction model longitudinal study
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 10 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈