Automated Extraction of Bio-entity Relationships from Literature

The current invention discloses an automated and standardized software application, system, and method of extracting relationships, for example bio-entity relationships, in text or literature.

The long-standing need for an improved, automated and more efficient text mining procedure is now met by a new and useful computer-implemented software application. The software is accessible from a non-transitory, computer-readable media and provides instructions for a computer processor to extract textual relationships or semantic information from non-annotated data by natural language processing and graph theoretic algorithm.

Advantages:

• The present invention may address one or more of the problems (high incidence of error and high cost of text mining), and deficiencies (low efficiency and poor organization/standardized format) of the prior art.

 Applications:

• Building biomedical databases, search engines, knowledge bases, or any other applications that may use organized relationships of content within literatures.