Towards Understandable Explanations for Document Analysis Systems

smartFIX is a product portfolio for knowledge based extraction of data from any document format. The system automatically determines the document type and extracts all relevant data for the respective business process. Data that is unreliably recognized is forwarded to a verification workplace for manual checking. In general, users have no difficulties to interpret the document data and wonder why the system needs additional input. For that reason, we implemented an explanation component that is used to justify extraction results, thus, increasing confidence of users. The component is using a semantic log making it possible to provide understandable explanations. We illustrate the benefits of that kind of technology in contrast to the current smartFIX Log Viewer by means of a preliminary user experiment.

[1]  Andreas Fordan.  Constraint Solving over OCR Graphs , 2001, INAP.

[2]  William B. Thompson,et al.  Reconstructive Expert System Explanation , 1992, Artif. Intell..

[3]  M. Gori,et al.  A two level knowledge approach for understanding documents of a multi-class domain , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[4]  P. Wright,et al.  Written information: Some alternatives to prose for expressing the outcomes of complex contingencies. , 1973 .

[5]  Johanna D. Moore,et al.  Explanations in knowledge systems: design for explainable expert systems , 1991, IEEE Expert.

[6]  Bertin Klein,et al.  smartFIX: An Adaptive System for Document Analysis and Understanding , 2004, Reading and Learning.

[7]  Haofen Wang,et al.  Top-k Exploration of Query Candidates for Efficient Keyword Search on Graph-Shaped (RDF) Data , 2009, 2009 IEEE 25th International Conference on Data Engineering.

[8]  Stephen W. Smoliar,et al.  Explanation: A Source of Guidance for Knowledge Representation , 1987, Knowledge Representation and Organization in Machine Learning.

[9]  Michael Gillmann,et al.  smartFIX statistics: towards systematic document analysis performance evaluation and optimization , 2010, DAS '10.

[10]  Andreas Dengel,et al.  Seizing the Treasure: Transferring Knowledge in Invoice Analysis , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[11]  Andreas Dengel,et al.  Semantic Logging: Towards Explanation-Aware DAS , 2011, 2011 International Conference on Document Analysis and Recognition.