Government Document

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 243 Experts worldwide ranked by ideXlab platform

Hank Young - One of the best experts on this subject based on the ideXlab platform.

Peng Wang - One of the best experts on this subject based on the ideXlab platform.

  • AIPR - Semi-supervised entity recognition of Chinese Government Document
    Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition - AIPR '19, 2019
    Co-Authors: Dagang Chen, Zeyuan Li, Zesong Li, Yajun Song, Peng Wang
    Abstract:

    There is a large amount of entity information in Government Documents. Identifying the entity information in Government Documents is the core foundation of intelligent Document processing tasks, such as word segmentation, semantic analysis and knowledge graph construction. To recognize entity, traditional Machine Learning algorithm has the advantage of relatively small tagging corpus requirement. However, this feature also means that this algorithm can hardly capture the implicit semantic information in sentences, which leads to the low accuracy of Document entity recognition. Also, this method requires tremendous manual work of feature designing. In contrast, Deep Learning algorithm needs a large tagging corpus. But it gives the algorithm ability to automatically acquire semantic feature information between context. So, the accuracy performance of entity recognition is greatly improved. Combining respective advantages of these above methods, this paper proposes a semi-supervised Deep Learning algorithm framework, which first implement the Conditional Random Field (CRF) and pseudo-labeling to expand the corpus, and then utilize the Dilated Convolution Neural Network (CNN) with Bi-directional Long Short-Term Memory (BiLSTM) plus CRF for extracting entities in official Documents. The experimental results show that, compared with other methods, the accuracy, recall rate and F1 value of entity recognition are improved by 5.02%, 5.85% and 5.44% respectively. The proposed method can effectively extract entity information in a Document.

  • semi supervised entity recognition of chinese Government Document
    International Conference on Artificial Intelligence, 2019
    Co-Authors: Dagang Chen, Yajun Song, Kunnan Liu, Peng Wang
    Abstract:

    There is a large amount of entity information in Government Documents. Identifying the entity information in Government Documents is the core foundation of intelligent Document processing tasks, such as word segmentation, semantic analysis and knowledge graph construction. To recognize entity, traditional Machine Learning algorithm has the advantage of relatively small tagging corpus requirement. However, this feature also means that this algorithm can hardly capture the implicit semantic information in sentences, which leads to the low accuracy of Document entity recognition. Also, this method requires tremendous manual work of feature designing. In contrast, Deep Learning algorithm needs a large tagging corpus. But it gives the algorithm ability to automatically acquire semantic feature information between context. So, the accuracy performance of entity recognition is greatly improved. Combining respective advantages of these above methods, this paper proposes a semi-supervised Deep Learning algorithm framework, which first implement the Conditional Random Field (CRF) and pseudo-labeling to expand the corpus, and then utilize the Dilated Convolution Neural Network (CNN) with Bi-directional Long Short-Term Memory (BiLSTM) plus CRF for extracting entities in official Documents. The experimental results show that, compared with other methods, the accuracy, recall rate and F1 value of entity recognition are improved by 5.02%, 5.85% and 5.44% respectively. The proposed method can effectively extract entity information in a Document.

Dagang Chen - One of the best experts on this subject based on the ideXlab platform.

  • AIPR - Semi-supervised entity recognition of Chinese Government Document
    Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition - AIPR '19, 2019
    Co-Authors: Dagang Chen, Zeyuan Li, Zesong Li, Yajun Song, Peng Wang
    Abstract:

    There is a large amount of entity information in Government Documents. Identifying the entity information in Government Documents is the core foundation of intelligent Document processing tasks, such as word segmentation, semantic analysis and knowledge graph construction. To recognize entity, traditional Machine Learning algorithm has the advantage of relatively small tagging corpus requirement. However, this feature also means that this algorithm can hardly capture the implicit semantic information in sentences, which leads to the low accuracy of Document entity recognition. Also, this method requires tremendous manual work of feature designing. In contrast, Deep Learning algorithm needs a large tagging corpus. But it gives the algorithm ability to automatically acquire semantic feature information between context. So, the accuracy performance of entity recognition is greatly improved. Combining respective advantages of these above methods, this paper proposes a semi-supervised Deep Learning algorithm framework, which first implement the Conditional Random Field (CRF) and pseudo-labeling to expand the corpus, and then utilize the Dilated Convolution Neural Network (CNN) with Bi-directional Long Short-Term Memory (BiLSTM) plus CRF for extracting entities in official Documents. The experimental results show that, compared with other methods, the accuracy, recall rate and F1 value of entity recognition are improved by 5.02%, 5.85% and 5.44% respectively. The proposed method can effectively extract entity information in a Document.

  • semi supervised entity recognition of chinese Government Document
    International Conference on Artificial Intelligence, 2019
    Co-Authors: Dagang Chen, Yajun Song, Kunnan Liu, Peng Wang
    Abstract:

    There is a large amount of entity information in Government Documents. Identifying the entity information in Government Documents is the core foundation of intelligent Document processing tasks, such as word segmentation, semantic analysis and knowledge graph construction. To recognize entity, traditional Machine Learning algorithm has the advantage of relatively small tagging corpus requirement. However, this feature also means that this algorithm can hardly capture the implicit semantic information in sentences, which leads to the low accuracy of Document entity recognition. Also, this method requires tremendous manual work of feature designing. In contrast, Deep Learning algorithm needs a large tagging corpus. But it gives the algorithm ability to automatically acquire semantic feature information between context. So, the accuracy performance of entity recognition is greatly improved. Combining respective advantages of these above methods, this paper proposes a semi-supervised Deep Learning algorithm framework, which first implement the Conditional Random Field (CRF) and pseudo-labeling to expand the corpus, and then utilize the Dilated Convolution Neural Network (CNN) with Bi-directional Long Short-Term Memory (BiLSTM) plus CRF for extracting entities in official Documents. The experimental results show that, compared with other methods, the accuracy, recall rate and F1 value of entity recognition are improved by 5.02%, 5.85% and 5.44% respectively. The proposed method can effectively extract entity information in a Document.

  • employing auto annotated data for Government Document classification
    Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence, 2019
    Co-Authors: Yajun Song, Xin Fang, Dagang Chen
    Abstract:

    In China, the Government Documents are Documents with legal effect and of standard forms formulated in the process of Government administration. With the continuous development of e-Government in China, Government database size increases hugely. To fully utilize the potential of the database, many applications based on natural language processing (NLP) are developed. Classification is a fundamental task for many NLP applications such as automatic Document archive, intelligent search, and personalized recommendation. Presently, in China, the Government Document classification method which based on issuing departments has very low accuracy. Traditional text classifiers based on machine learning or deep learning models rely heavily on human-labeled training data. While there are no open data sets on the Government Documents, we propose a method to automatically constructing large-scale annotated data set for Government Document classification based on the information retrieval method. Experiment results show that the supervised classification model trained on our automatically constructed data set outperforms the baseline method 15% on F1-score.

Eugene Sawa - One of the best experts on this subject based on the ideXlab platform.

Geetha Subramaniam - One of the best experts on this subject based on the ideXlab platform.

  • Work Load Analysis for Determining the Optimal Employee Number – A Case of Faculty of Economics Pakuan University Bogor, Indonesia
    ADVANCES IN BUSINESS RESEARCH INTERNATIONAL JOURNAL, 2020
    Co-Authors: Herman Herman, Geetha Subramaniam
    Abstract:

    Generally, the number of employees in an organisation needs to be based on the workload of the administrative staff and this is practised at the Economic Faculty Pakuan University, Indonesia too. To calculate the activity time of employees who work or not, researchers use the work sampling table. The method of calculating labour requirements is based on the calculation of the workload with the task per duty of the office according to Government guidelines. In Indonesia, the guidelines are spelt out in detail in the Government Document MenPAN No. KEP/75/M.PAN/7/2004 namely the “Guidelines for Employee Needs Calculation”. Samples on employee status were extracted from the Economics Faculty of the Pakuan University from the principal administrative officer. Data was processed using Microsoft Excel. The study concluded that there is a significant result in the use of working time and found that the University had the required number of employees it needed whereby 3 functions of services were done by 9 persons. Based on the calculation of the workload analysis, one more employee is needed for the financial services. It was also noted that efficiency level for effective working hours for administrative staff is 28 hours per week or 1680 minutes and there is a smooth workload administration at the Faculty of Economics. However, an additional employee in the Administration Department and an additional academic staff will increase the efficiency of employees in the Faculty.

  • work load analysis for determining the optimal employee number a case of faculty of economics pakuan university bogor indonesia herman and geetha subramaniam
    2018
    Co-Authors: Herman Herman, Geetha Subramaniam
    Abstract:

    Generally, the number of employees in an organisation needs to be based on the workload of the administrative staff and this is practised at the Economic Faculty Pakuan University, Indonesia too. To calculate the activity time of employees who work or not, researchers use the work sampling table. The method of calculating labour requirements is based on the calculation of the workload with the task per duty of the office according to Government guidelines. In Indonesia, the guidelines are spelt out in detail in the Government Document MenPAN No. KEP/75/M.PAN/7/2004 namely the “Guidelines for Employee Needs Calculation”. Samples on employee status were extracted from the Economics Faculty of the Pakuan University from the principal administrative officer. Data was processed using Microsoft Excel. The study concluded that there is a significant result in the use of working time and found that the University had the required number of employees it needed whereby 3 functions of services were done by 9 persons. Based on the calculation of the workload analysis, one more employee is needed for the financial services. It was also noted that efficiency level for effective working hours for administrative staff is 28 hours per week or 1680 minutes and there is a smooth workload administration at the Faculty of Economics. However, an additional employee in the Administration Department and an additional academic staff will increase the efficiency of employees in the Faculty.

Related terms

Government Document - 15 days free trial to Access Experts & Abstracts