资源类型

期刊论文 115

会议视频 2

年份

2023 9

2022 11

2021 8

2020 4

2019 4

2018 13

2017 8

2016 4

2015 7

2014 4

2013 3

2012 9

2011 5

2010 3

2009 3

2008 5

2007 6

2006 2

2005 2

2004 3

展开 ︾

关键词

特征抽取 3

特征提取 3

人脸识别 2

微地震监测 2

提取 2

水驱前缘 2

注水开发 2

萃取 2

7815 1

CECE-GC 1

DQP漂白 1

IKPCA 1

KPCA 1

KP法制浆 1

T试剂 1

主题提取；主题演化；评价方法 1

井底裂缝连通 1

产品制备 1

优势度 1

展开 ︾

检索范围：

排序： 展示方式：

Entity and relation extraction with rule-guided dictionary as domain knowledge

《工程管理前沿（英文）》   页码 610-622 doi: 10.1007/s42524-022-0226-0

摘要： Entity and relation extraction is an indispensable part of domain knowledge graph construction, which can serve relevant knowledge needs in a specific domain, such as providing support for product research, sales, risk control, and domain hotspot analysis. The existing entity and relation extraction methods that depend on pretrained models have shown promising performance on open datasets. However, the performance of these methods degrades when they face domain-specific datasets. Entity extraction models treat characters as basic semantic units while ignoring known character dependency in specific domains. Relation extraction is based on the hypothesis that the relations hidden in sentences are unified, thereby neglecting that relations may be diverse in different entity tuples. To address the problems above, this paper first introduced prior knowledge composed of domain dictionaries to enhance characters’ dependence. Second, domain rules were built to eliminate noise in entity relations and promote potential entity relation extraction. Finally, experiments were designed to verify the effectiveness of our proposed methods. Experimental results on two domains, including laser industry and unmanned ship, showed the superiority of our methods. The F1 value on laser industry entity, unmanned ship entity, laser industry relation, and unmanned ship relation datasets is improved by +1%, +6%, +2%, and +1%, respectively. In addition, the extraction accuracy of entity relation triplet reaches 83% and 76% on laser industry entity pair and unmanned ship entity pair datasets, respectively.

关键词： entity extraction     relation extraction     prior knowledge     domain rule    

HTML PDF 收藏

Automatically building large-scale named entity recognition corpora from Chinese Wikipedia

Jie ZHOU,Bi-cheng LI,Gang CHEN

《信息与电子工程前沿（英文）》 2015年 第16卷 第11期   页码 940-956 doi: 10.1631/FITEE.1500067

摘要： Named entity recognition (NER) is a core component in many natural language processing applications. Most NER systems rely on supervised machine learning methods, which depend on time-consuming and expensive annotations in different languages and domains. This paper presents a method for automatically building silver-standard NER corpora from Chinese Wikipedia. We refine novel and language-dependent features by exploiting the text and structure of Chinese Wikipedia. To reduce tagging errors caused by entity classification, we design four types of heuristic rules based on the characteristics of Chinese Wikipedia and train a supervised NE classifier, and a combined method is used to improve the precision and coverage. Then, we realize type identification of implicit mention by using boundary information of outgoing links. By selecting the sentences related with the domains of test data, we can train better NER models. In the experiments, large-scale NER corpora containing 2.3 million sentences are built from Chinese Wikipedia. The results show the effectiveness of automatically annotated corpora, and the trained NER models achieve the best performance when combining our silver-standard corpora with gold-standard corpora.

关键词： NER corpora     Chinese Wikipedia     Entity classification     Domain adaptation     Corpus selection    

HTML PDF 收藏

Named entity recognition for Chinese construction documents based on conditional random field

《工程管理前沿（英文）》 2023年 第10卷 第2期   页码 237-249 doi: 10.1007/s42524-021-0179-8

摘要： Named entity recognition (NER) is essential in many natural language processing (NLP) tasks such as information extraction and document classification. A construction document usually contains critical named entities, and an effective NER method can provide a solid foundation for downstream applications to improve construction management efficiency. This study presents a NER method for Chinese construction documents based on conditional random field (CRF), including a corpus design pipeline and a CRF model. The corpus design pipeline identifies typical NER tasks in construction management, enables word-based tokenization, and controls the annotation consistency with a newly designed annotating specification. The CRF model engineers nine transformation features and seven classes of state features, covering the impacts of word position, part-of-speech (POS), and word/character states within the context. The F1-measure on a labeled construction data set is 87.9%. Furthermore, as more domain knowledge features are infused, the marginal performance improvement of including POS information will decrease, leading to a promising research direction of POS customization to improve NLP performance with limited data.

关键词： NER     NLP     Chinese language     construction document    

HTML PDF 收藏

利用两个自适应特征改进实体链接 Research Article

张鸿彬,陈权,张伟文

《信息与电子工程前沿（英文）》 2022年 第23卷 第11期   页码 1620-1630 doi: 10.1631/FITEE.2100495

摘要：

实体链接是自然语言处理中的一项基本任务。现有的基于神经网络的系统更多地关注全局模型的构建，而忽略了局部模型中潜在的语义信息和有效实体类型信息的获取。本文提出两个自适应特征，其中第一个自适应特征使得局部和全局模型能够捕获潜在信息，第二个自适应特征能够描述实体类型嵌入的有效信息。这些自适应特征可以很自然地协同工作来处理一些不确定的实体类型信息。实验结果表明，我们的实体链接系统在AIDA-B和MSNBC数据集上取得了最佳的性能，并在域外数据集上达到了最佳的平均性能。这些结果表明，所提出的自适应特征能够基于其自身不同的上下文来捕获有利于实体链接的信息。

关键词： 实体链接；局部模型；全局模型；自适应特征；实体类型    

HTML PDF 收藏

An extraction- assay system: Evaluation on flavonols in plant resistance to Pb and Cd by supercriticalextraction- gas chromatography

Xu Zhang, Huanhuan Yang, Xinlei Wang, Wen Song, Zhaojie Cui

《环境科学与工程前沿（英文）》 2018年 第12卷 第4期 doi: 10.1007/s11783-018-1059-2

摘要：

SFE-GC system is established for flavonols assessment.

Optimal parameters of SFE-GC are evaluated and determined.

Quercetin and kaempferol are detected in plant under heavy metal stress.

Gene expression analysis shows consistent regularity with content of flavonols.

ROS level is applied for elaborating the plant resistance status.

关键词： Flavonols     Heavy metal     Supercritical carbon dioxide extraction (SFE)     GC     Plant resistance    

HTML PDF 收藏

一种构件化的坑道工程动荷段实体模型设计质量判决方法

袁 辉,王凤山,许继恒,付成群

《中国工程科学》 2013年 第15卷 第5期   页码 106-112

摘要：

为有效表示坑道工程空间对象，并有效支持动荷段实体的各种拓扑操作和毁伤分析等军事应用，提出了坑道工程动荷段实体模型构件化设计解决方案和设计质量的直觉模糊判决方法。适应坑道工程动荷段实体模型构件化设计的多样性特征和有效性验证约束，确定直觉模糊的正负理想构件化设计事件，比较构件化设计事件与正负理想事件的距离，建立坑道工程动荷段实体模型构件化设计事件的优势度计算模型，进而得到构件化设计事件集合的序列。案例表明，方法有效解决了坑道工程动荷段实体模型构件化设计质量判决问题，为科学的坑道工程动荷段实体模型设计实践提供了一种理论和方法。

关键词： 坑道工程     构件     设计质量     实体模型     直觉模糊集     优势度    

HTML PDF 收藏

Feature extraction from slice data for reverse engineering

ZHANG Yingjie, LU Shangning

《机械工程前沿（英文）》 2007年 第2卷 第1期   页码 25-31 doi: 10.1007/s11465-007-0004-z

摘要： A new approach to feature extraction for slice data points is presented. The reconstruction of objects is performed as follows. First, all contours in each slice are extracted by contour tracing algorithms. Then the data points on the contours are analyzed, and the curve segments of the contours are divided into three categories: straight lines, conic curves and B-spline curves. The curve fitting methods are applied for each curve segment to remove the unwanted points with pre-determined tolerance. Finally, the features, which consist of the object and connection relations among them, are founded by matching the corresponding contours in adjacent slices, and 3D models are reconstructed based on the features. The proposed approach has been implemented in OpenGL, and the feasibility of the proposed method has been verified by several cases.

关键词： feasibility     corresponding     B-spline     pre-determined tolerance     extraction    

HTML PDF 收藏

A microextraction approach for rapid extraction and separation of Mn(II) and Co(II) using saponified

《化学科学与工程前沿（英文）》 2022年 第16卷 第6期   页码 963-972 doi: 10.1007/s11705-021-2081-7

摘要： In this paper, we proposed a microextraction approach for the extraction and separation of Mn(II) and Co(II) from sulfate solution simulating leachate of spent lithium-ion battery cathode materials using saponified di-(2-ethylhexyl)phosphoric acid system. The effects of the following operational variables were investigated: equilibrium pH, tri-n-butyl phosphate concentration, saponification rate, two-phase ratio and residence time. The results showcased that the microextractor can reach the extraction equilibrium within 20 s, thereby greatly reducing necessary extraction time comparing to that of conventional processes. The volumetric mass transfer coefficient showed 8–21 times larger than that of batch device. With the help of microextractor, 95% of Mn(II) was extracted with a single theoretical stage at a chosen two-phase ratio of 3:1, and the separation factor βMn/Co was as large as 65.5. In the subsequent stripping step, more than 99% of manganese from loaded phase was easily stripped under optimal conditions. The microextraction approach greatly enhances the mass transfer while enabling a continuous and controllable extraction process within a simple structure design. When extracting spent electrode material with microextractors, the comprehensive recovery of mangenese can reach 96%. The microextraction approach has a good applicability in the spent lithium-ion battery cathode materials recycling at both bench and industrial scales.

关键词： extraction equilibrium     mass transfer coefficient     microextraction     multicomponent extraction     di-(2-ethylhexyl)phosphoric acid    

HTML PDF 收藏

一种基于特征模板和CNN-BiLSTM-CRF的网络安全实体识别方法 Research Papers

Ya QIN, Guo-wei SHEN, Wen-bo ZHAO, Yan-ping CHEN, Miao YU, Xin JIN

《信息与电子工程前沿（英文）》 2019年 第20卷 第6期   页码 872-884 doi: 10.1631/FITEE.1800520

摘要： 利用海量网络安全威胁情报数据，构建网络安全知识图谱实施深度关联分析和挖掘，可帮助识别安全威胁并提出相应防御措施。这已成为网络安全领域研究热点。本文针对网络安全文本数据，研究实体识别算法，为构建网络安全知识图谱奠定基础。传统方法难以识别网络安全领域的新实体、中英文混合安全实体等，且提取的特征不够充分。本文在神经网络模型基础上，提出基于特征模板的CNN-BiLSTM-CRF网络安全实体识别算法。首先构建人工特征模板，提取局部上下文特征。再利用CNN提取字符特征，与局部上下文特征结合，传入BiLSTM模型提取语义特征。最后利用CRF对安全实体进行标注。结果表明，在大规模网络安全数据集上，该方法优于其它算法，F值达到86%。

关键词： 网络安全知识图谱；网络安全实体；特征模板；实体识别；神经网络    

HTML PDF 收藏

Performance evaluation of an improved biomass-fired cogeneration system simultaneously using extraction

《能源前沿（英文）》 2022年 第16卷 第2期   页码 321-335 doi: 10.1007/s11708-021-0741-4

摘要： An advanced cogeneration system based on biomass direct combustion was developed and its feasibility was demonstrated. In place of the traditional single heat source (extraction steam), the extraction steam from the turbine, the cooling water from the plant condenser, and the low-pressure feedwater from the feedwater preheating system were collectively used for producing district heat in the new scheme. Hence, a remarkable energy-saving effect could be achieved, improving the overall efficiency of the cogeneration system. The thermodynamic and economic performance of the novel system was examined when taking a 35 MW biomass-fired cogeneration unit for case study. Once the biomass feed rate and net thermal production remain constant, an increment of 1.36 MW can be expected in the net electric production, because of the recommended upgrading. Consequently, the total system efficiency and effective electrical efficiency augmented by 1.23 and 1.50 percentage points. The inherent mechanism of performance enhancement was investigated from the energy and exergy aspects. The economic study indicates that the dynamic payback period of the retrofitting project is merely 1.20 years, with a net present value of 5796.0 k$. In conclusion, the proposed concept is validated to be advantageous and profitable.

关键词： biomass-fired cogeneration     district heat production system     absorption heat pump     extraction steam     cooling water     low-pressure feedwater    

HTML PDF 收藏

Study of an artificial boundary condition based on the damping-solvent extraction method

Qiang XU, Jianyun CHEN, Jing LI, Mingming WANG

《结构与土木工程前沿（英文）》 2012年 第6卷 第3期   页码 281-287 doi: 10.1007/s11709-012-0167-5

摘要： A new artificial boundary condition for time domain analysis of a structure-unlimited-foundation system was proposed. The boundary condition was based on the damping-solvent extraction method. The principle of the damping-solvent extraction method was described. An artificial boundary condition was then established by setting two spring-damper systems and one artificial damping limited region. A test example was developed to verify that the proposed boundary condition and model had high precision. Compared with the damping-solvent extraction method, this boundary condition is easier to be applied to finite element method (FEM)-based numerical calculations.

关键词： damping-solvent extraction method     structure-unlimited-foundation system     spring-damper system     artificial damping limited region     finite element method    

HTML PDF 收藏

Study on the microwave-assisted extraction of polyphenols from tea

Liyun WANG, Peiyong QIN, Yan HU,

《化学科学与工程前沿（英文）》 2010年 第4卷 第3期   页码 307-313 doi: 10.1007/s11705-009-0282-6

摘要： This study demonstrated a promising method for quickly extracting tea polyphenol (TP) by microwave-assisted extraction (MAE) technology. Some influential parameters, including MAE temperature, microwave power, concentration of extraction solvent, MAE time and the solid/liquid ratio, were investigated. The optimum condition of MAE was obtained by dual extraction with 60% ethanol (v/v) and the solid/liquid ratio 1:12 g/mL at 80°C for 10 minutes under the microwave power 600 W. The yield of TP was 96.5% under the described condition. Compared with traditional methods, including hot reflux extraction (HRE), ultrasound-assisted extraction (UAE) and supercritical fluid extraction (SFE), the extraction time was saved 8 times than that of HRE, and the yield was increased by 17.5%. The extraction time at comparable levels of production was saved 2 times, and the energy consumption was one fourth that of UAE. The extraction time was saved 5 times than that of SFE, and the yield of TP was increased by 40%. Moreover, compared with MAE of TP studied by others, it decreased the solid/liquid ratio from 1 ∶ 20 to 1 ∶ 12 g/mL without 90-min pre-leaching time, and the yield of TP was increased by 6%–40%.

关键词： energy consumption     microwave-assisted extraction     optimum condition     pre-leaching     concentration    

HTML PDF 收藏

Oxidation-extraction desulfurization of model oil over Zr-ZSM-5/SBA-15 and kinetic study

Chuanzhu LU,Hui FU,Huipeng LI,Hua ZHAO,Tianfeng CAI

《化学科学与工程前沿（英文）》 2014年 第8卷 第2期   页码 203-211 doi: 10.1007/s11705-014-1420-3

摘要： ZSM-5/SBA-15 composite molecular sieves were synthesized using post-synthesis method and characterized by X-ray diffraction and N adsorption-desorption. The oxidative-extration desulfurization of model oil was investigated by using hydrogen peroxide as the oxidant, tetrabutyl ammonium bromide as phase transfer catalyst, dimethyl sulfoxide as extractant, and Zr-ZSM-5/SBA-15, Ag-ZSM-5/SBA-15, Ce-ZSM-5/SBA-15 as catalyst. Under the optimal conditions, the desulfurization rate decreases in the order: Zr-ZSM-5/SBA-15>Ce-ZSM-5/SBA-15>Ag-ZSM-5/SBA-15. The highest desulfurization rate is 84.53% under the catalysis of Zr-ZSM-5/SBA-15. Kinetics analysis shows that the reaction is pseudo-first-order with the activation energy of 44.23 kJ/mol.

关键词： composite molecular sieve     oxidation desulfuration     extraction     kinetic    

HTML PDF 收藏

Extraction of hydrogen chloride by a coupled reaction-solvent extraction process

Yunzhao Li,Xingfu Song,Guilan Chen,Shuying Sun,Yanxia Xu,Jianguo Yu

《化学科学与工程前沿（英文）》 2015年 第9卷 第4期   页码 479-487 doi: 10.1007/s11705-015-1512-8

摘要： A coupled reaction-solvent extraction process was used to remove HCl from a simulated distiller waste. The extraction performances of various extractants and diluents were compared and the apparent basicity of N235 (a mixture of tertiary amines) in various diluents was determined. The best results were obtained using N235 and isoamyl alcohol as the extractant and diluent, respectively. The yield of HCl from the coupled extraction was 75% with this extraction system. The mechanisms for the removal of HCl in both the direct and coupled extractions were investigated. For the coupled extraction, the formation of an R NHCl ion-pair complex was involved in the HCl removal. For the direct extraction, the mechanism involved the formation of hydrogen bonds at high concentrations of HCl.

关键词： hydrogen chloride     distiller waste     coupled reaction and solvent extraction     N235     extraction mechanism    

HTML PDF 收藏

Surface molecularly imprinted polymers for solid-phase extraction of (--)-epigallocatechin gallate from

Yunling Gao,Ying Hu,Kejian Yao

《化学科学与工程前沿（英文）》 2015年 第9卷 第4期   页码 467-478 doi: 10.1007/s11705-015-1526-2

摘要： Surface molecularly imprinted polymers (SMIPs) have been synthesized to selectively determine (−)-epigallocatechin gallate in aqueous media. SMIPs were prepared using a surface grafting copolymerization method on a functionalized silica gel modified with -cyclodextrin and vinyl groups. The morphology and composition of the SMIPs were investigated by scanning electron microscopy, Fourier transform-infrared spectroscopy and thermogravimetric analysis. In addition, the molecular binding capacity, recognition properties and selectivity of the SMIPs were evaluated. The imprinted polymers were found to have a highly specific recognition and binding capacity for (−)-epigallocatechin gallate in aqueous media which is the result of the hydrophobic properties of the -cyclodextrin and the hydrogen-bonding interactions of methacrylic acid. The SMIPs were successfully employed as solid-phase extraction adsorbents prior to the HPLC determination of (−)-epigallocatechin gallate in toothpaste. The HPLC analysis had a linear dynamic range of 0.5–50.0 µg?mL with a correlation coefficient of 0.9998 and the recoveries ranged from 89.4% to 97.0% with relative standard deviations less than 4.8%. The limit of detection and limit of quantification were 0.17 and 0.33 µg?mL , respectively. The method provides a promising approach for the preparation of selective materials for the purification and determination of complex samples.

关键词： β-cyclodextrin     (−)-epigallocatechin gallate     surface molecular imprinting     solid-phase extraction    

HTML PDF 收藏

标题 作者 时间 类型 操作

Entity and relation extraction with rule-guided dictionary as domain knowledge

期刊论文

Automatically building large-scale named entity recognition corpora from Chinese Wikipedia

Jie ZHOU,Bi-cheng LI,Gang CHEN

期刊论文

Named entity recognition for Chinese construction documents based on conditional random field

期刊论文

利用两个自适应特征改进实体链接

张鸿彬,陈权,张伟文

期刊论文

An extraction- assay system: Evaluation on flavonols in plant resistance to Pb and Cd by supercriticalextraction- gas chromatography

Xu Zhang, Huanhuan Yang, Xinlei Wang, Wen Song, Zhaojie Cui

期刊论文

一种构件化的坑道工程动荷段实体模型设计质量判决方法

袁 辉,王凤山,许继恒,付成群

期刊论文

Feature extraction from slice data for reverse engineering

ZHANG Yingjie, LU Shangning

期刊论文

A microextraction approach for rapid extraction and separation of Mn(II) and Co(II) using saponified

期刊论文

一种基于特征模板和CNN-BiLSTM-CRF的网络安全实体识别方法

Ya QIN, Guo-wei SHEN, Wen-bo ZHAO, Yan-ping CHEN, Miao YU, Xin JIN

期刊论文

Performance evaluation of an improved biomass-fired cogeneration system simultaneously using extraction

期刊论文

Study of an artificial boundary condition based on the damping-solvent extraction method

Qiang XU, Jianyun CHEN, Jing LI, Mingming WANG

期刊论文

Study on the microwave-assisted extraction of polyphenols from tea

Liyun WANG, Peiyong QIN, Yan HU,

期刊论文

Oxidation-extraction desulfurization of model oil over Zr-ZSM-5/SBA-15 and kinetic study

Chuanzhu LU,Hui FU,Huipeng LI,Hua ZHAO,Tianfeng CAI

期刊论文

Extraction of hydrogen chloride by a coupled reaction-solvent extraction process

Yunzhao Li,Xingfu Song,Guilan Chen,Shuying Sun,Yanxia Xu,Jianguo Yu

期刊论文

Surface molecularly imprinted polymers for solid-phase extraction of (--)-epigallocatechin gallate from

Yunling Gao,Ying Hu,Kejian Yao

期刊论文