Academic Activities Transaction Extraction Based on Deep Belief Network
Extracting information about academic activity transactions from unstructured documents is a key problem in the analysis of academic behaviors of researchers. The academic activities transaction includes five elements: person, activities, objects, attributes, and time phrases. The traditional method...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2017/5067069 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551687699562496 |
|---|---|
| author | Xiangqian Wang Fang Huang Wencong Wan Chengyuan Zhang |
| author_facet | Xiangqian Wang Fang Huang Wencong Wan Chengyuan Zhang |
| author_sort | Xiangqian Wang |
| collection | DOAJ |
| description | Extracting information about academic activity transactions from unstructured documents is a key problem in the analysis of academic behaviors of researchers. The academic activities transaction includes five elements: person, activities, objects, attributes, and time phrases. The traditional method of information extraction is to extract shallow text features and then to recognize advanced features from text with supervision. Since the information processing of different levels is completed in steps, the error generated from various steps will be accumulated and affect the accuracy of final results. However, because Deep Belief Network (DBN) model has the ability to automatically unsupervise learning of the advanced features from shallow text features, the model is employed to extract the academic activities transaction. In addition, we use character-based feature to describe the raw features of named entities of academic activity, so as to improve the accuracy of named entity recognition. In this paper, the accuracy of the academic activities extraction is compared by using character-based feature vector and word-based feature vector to express the text features, respectively, and with the traditional text information extraction based on Conditional Random Fields. The results show that DBN model is more effective for the extraction of academic activities transaction information. |
| format | Article |
| id | doaj-art-93c6b197da154125bc2686863b8997a0 |
| institution | Kabale University |
| issn | 1687-5680 1687-5699 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj-art-93c6b197da154125bc2686863b8997a02025-02-03T06:00:52ZengWileyAdvances in Multimedia1687-56801687-56992017-01-01201710.1155/2017/50670695067069Academic Activities Transaction Extraction Based on Deep Belief NetworkXiangqian Wang0Fang Huang1Wencong Wan2Chengyuan Zhang3School of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Information Science and Engineering, Central South University, Changsha 410083, ChinaExtracting information about academic activity transactions from unstructured documents is a key problem in the analysis of academic behaviors of researchers. The academic activities transaction includes five elements: person, activities, objects, attributes, and time phrases. The traditional method of information extraction is to extract shallow text features and then to recognize advanced features from text with supervision. Since the information processing of different levels is completed in steps, the error generated from various steps will be accumulated and affect the accuracy of final results. However, because Deep Belief Network (DBN) model has the ability to automatically unsupervise learning of the advanced features from shallow text features, the model is employed to extract the academic activities transaction. In addition, we use character-based feature to describe the raw features of named entities of academic activity, so as to improve the accuracy of named entity recognition. In this paper, the accuracy of the academic activities extraction is compared by using character-based feature vector and word-based feature vector to express the text features, respectively, and with the traditional text information extraction based on Conditional Random Fields. The results show that DBN model is more effective for the extraction of academic activities transaction information.http://dx.doi.org/10.1155/2017/5067069 |
| spellingShingle | Xiangqian Wang Fang Huang Wencong Wan Chengyuan Zhang Academic Activities Transaction Extraction Based on Deep Belief Network Advances in Multimedia |
| title | Academic Activities Transaction Extraction Based on Deep Belief Network |
| title_full | Academic Activities Transaction Extraction Based on Deep Belief Network |
| title_fullStr | Academic Activities Transaction Extraction Based on Deep Belief Network |
| title_full_unstemmed | Academic Activities Transaction Extraction Based on Deep Belief Network |
| title_short | Academic Activities Transaction Extraction Based on Deep Belief Network |
| title_sort | academic activities transaction extraction based on deep belief network |
| url | http://dx.doi.org/10.1155/2017/5067069 |
| work_keys_str_mv | AT xiangqianwang academicactivitiestransactionextractionbasedondeepbeliefnetwork AT fanghuang academicactivitiestransactionextractionbasedondeepbeliefnetwork AT wencongwan academicactivitiestransactionextractionbasedondeepbeliefnetwork AT chengyuanzhang academicactivitiestransactionextractionbasedondeepbeliefnetwork |