Browse Prior Art Database

Method and System for Detecting Enumeration and Bullet Lists in Structured and Unstructured Texts

IP.com Disclosure Number: IPCOM000236376D
Publication Date: 2014-Apr-23
Document File: 3 page(s) / 75K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method and system is disclosed for detecting enumeration and bullet lists in structured and unstructured texts.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

Method and System for Detecting Enumeration and Bullet Lists in Structured and Unstructured Texts

An automated detection of enumeration lists and bullet lists is required for effective automated text reading and information extraction . The automated detection of enumeration lists and bullet lists is also required for the deployment of technologies based on Natural Language Processing (NLP). The hierarchical relationship between different entities is inherent to the enumeration and bullet lists . The hierarchical relationship can be used to build better semantic models and knowledge representation of content in a text. The semantic models and knowledge representation of the content in the text are required for better understanding of the text by machines and computing technologies.

Disclosed is a method and system for detecting enumeration and bullet lists in structured and unstructured texts. The method and system automatically detects an enumeration list, given a structured or unstructured text. The enumeration list can be, but is not limited to, punctuated vertical lists, vertical lists, outlines, in%text lists and bullet list with one or more levels. The method and system is also capable of detecting a tree structure and producing a machine readable output of the enumeration list . The method and system detects the enumeration list by recognizing succession items such as, but not limited to, numbers, letters, bullets and punctuations.

Fig. 1 illustrates a flow diagram of a process of detecting enumeration lists and transformation of the enumeration lists into a valid assignment tree .

1


Page 02 of 3

Figure 1

The method and system identifies every an...