Each day hundred thousands of customer transactions arrive at banks operation center via fax channel. The information required to complete each transaction (money transfer, salary payment, tax payment etc.) is extracted manually by operators from the image of customer orders. Our information extraction system uses CRFs (Conditional Random Fields) for obtaining the required named entities for each transaction type from noisy text of customer orders. The difficulty of the problem arouses from the fact that every customer order has different formats, image resolution of orders are so low that OCR-ed (Optical Character Recognition) texts are highly noisy and Turkish is still challenging for the natural language processing techniques due to structure of the language. This paper mentions the difficulties of our problem domain and provides details of the methodology developed for extracting entities such as client name, organization name, bank account number, IBAN number, amount, currency and explanation.
CITATION STYLE
Emekligil, E., Arslan, S., & Agin, O. (2016). A bank information extraction system based on named entity recognition with CRFs from noisy customer order texts in Turkish. In Communications in Computer and Information Science (Vol. 649, pp. 93–102). Springer Verlag. https://doi.org/10.1007/978-3-319-45880-9_8
Mendeley helps you to discover research relevant for your work.