论文信息 - Automatic redaction of private information using relational information extraction

Automatic redaction of private information using relational information extraction

We report on an attempt to build an automatic redaction system by applying information extraction techniques to the identification of private dates of birth. We conclude that automatic redaction is a promising concept although information extraction is significantly affected by the presence of OCR error.

[1] Kazem Taghva,et al. The Effects of OCR Error on the Extraction of Private Information , 2006, Document Analysis Systems.

[2] Feng Zhang,et al. A New Statistical Approach to Personal Name Extraction , 2002, ICML.

[3] William W. Cohen,et al. Extracting Personal Names from Email: Applying Named Entity Recognition to Informal Text , 2005, HLT.

[4] Kazem Taghva,et al. OCR correction based on document level knowledge , 2003, IS&T/SPIE Electronic Imaging.

[5] Kazem Taghva,et al. OCRSpell: an interactive spelling correction system for OCR errors in text , 2001, International Journal on Document Analysis and Recognition.

[6] Kazem Taghva,et al. Evaluation of model-based retrieval effectiveness with OCR text , 1996, TOIS.

[7] Kazem Taghva,et al. Information access in the presence of OCR errors , 2004, HDP '04.

[8] Ralph Grishman,et al. Information Extraction: Techniques and Challenges , 1997, SCIE.

[9] Nancy Chinchor,et al. Overview of MUC-7 , 1998, MUC.

[10] Kazem Taghva,et al. Effects of OCR Errors on Ranking and Feedback Using the Vector Space Model , 1996, Inf. Process. Manag..