Original Contribution: Stacked generalization
Neural Networks
BoosTexter: A Boosting-based Systemfor Text Categorization
Machine Learning - Special issue on information retrieval
Japanese Named Entity extraction with redundant morphological analysis
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Named entity extraction based on a maximum entropy model and transformation rules
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Hi-index | 0.00 |
This paper presents an assistant tool for concealing personal information in text. Concealing personal information is one of the important roles for protecting privacy in disclosure of public documents, protection of accidental personal information leakages, and so on. However, concealing personal information is very time-consuming, because it is strongly depending on manpower. In order to alleviate tasks of concealing personal information, we have developed a graphical user interface (GUI) tool that has the following three characteristics: 1) Extracting candidates of personal information in text. 2) Presenting the candidates with colors indicating types of personal information. 3) Creating extraction rules for personal information from text including annotations of personal information. The experimental results on tasks of concealing person names in Japanese text showed that processing times of concealing personal names with candidates of person names were about 1.5 to 3.9 times faster than without candidates of person names.