Authors:
Wessel Stoop
1
;
Iris Hendrickx
2
and
Tom van Ees
3
Affiliations:
1
Davinci Products and Radboud University, Netherlands
;
2
Radboud University, Netherlands
;
3
Davinci Products, Netherlands
Keyword(s):
Dossier Reorganizing, Text Classification, Pagenumber Classification, Customer Document Processing.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Economics, Business and Forecasting Applications
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Learning in Process Automation
;
Natural Language Processing
;
Pattern Recognition
;
Software Engineering
;
Symbolic Systems
Abstract:
We investigate the creation of a robust algorithm for document identification and page ordering in a digital mail room in the banking sector. PaperClip is a system that takes files containing pages of various documents as input, and returns multiple files that contain all the pages of one document in the correct order. PaperClip performs (1) document type classification and (2) page number classification on each page, and then (3) merges the results. We experimented with various algorithms and methods for these three steps and we performed an elaborate evaluation to measure different aspects of the methods. The best performing setup achieved a cut F-score of 86\% and a V-measure of 0.91\% . This is high enough to fulfill business needs of the banking sector.