Automatically Extracting Structure and Data from Business Reports

Overview

Business Reports

Business Reports

Business Reports

Business Reports

Business-Report Structure

Type I Reports

Type II Reports

Structure Extraction Process

Data Extraction Process

Delimitations

Algorithm 1: Extract Fields

Field Extraction

Algorithm 2: Infer Line Types

Infer Basic Line Types

Algorithm 3: Infer Page Headers/Footers

Page Headers/Footers

Algorithm 4: Infer Group Structure (uvkw)

Inferring Group Structure

Experiment

Experimental Results

Interpretation of Results

Future Work

Data Extraction Group