Rule Based Chunk Extraction from PDF Documents Using Regular Expressions and Natural Language Processing

摘要

The Natural Language Processing (NLP) is a stimulating and vital field of Artificial Intelligence (AI).The NLP can be used to find out the required intelligence through the system under consideration,so that system behaves as per convenience and efficiency expected by the user.The proposed system demonstrates application of NLP and by using Regular Expressions to categorize and classify sentences in Word/PDF (Portable Document Format) documents according to rules provided by user.Thousands of similar kind of PDF documents can be easily processed by reading them page wise,the proposed system produces results according to the user defined rules those are applicable to all input PDF documents.Single rule is written by considering one input PDF document and apply the same to all other input PDF documents of the proposed system to create individual data chunks out of all documents and display them on User Interface in table format.