Domain adaptation of web data extraction based on bootstrapping method
- DOI
- 10.2991/eeeis-16.2017.49How to use a DOI?
- Keywords
- Domain Adaptation; Web Data Extraction; Bootstrapping; Electric Power Enterprise Information; Wrapper.
- Abstract
With the fast development of electric power enterprise information, special structured storage and management system is becoming more and more important. As a uniform interface for multitude of data sources, the efficiency to extract unstructured and semi-structured data existing in webpage is a key issue for Web data integration. In this paper, we grope for the problem of constructing domain adaptation wrappers for web information extraction. We design the domain adaptation extraction framework based on bootstrapping method. Meanwhile, we discuss the main technologies. By obtaining the extraction model for recruitment site and then random sampling pages at other power system sites using this extraction model for training the new wrapper, a uniform data accessing infrastructure in power system domain can be built. In addition, the wrapper has high multipurpose, realizing the domain adaptation extraction. Experimental results show that the proposed approach can improve the extraction accuracy of target data and effectively solve the adaptive wrapper for the massive Web data in various fields.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Dong-Lan Liu AU - Xin Liu AU - Lei Ma AU - Hao Yu AU - Yong Zhao AU - Guo-Dong Lv PY - 2016/12 DA - 2016/12 TI - Domain adaptation of web data extraction based on bootstrapping method BT - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016) PB - Atlantis Press SP - 372 EP - 385 SN - 2352-5401 UR - https://doi.org/10.2991/eeeis-16.2017.49 DO - 10.2991/eeeis-16.2017.49 ID - Liu2016/12 ER -