What Is Knowledge Extraction?

Article Details
  • Written By: Malcolm Tatum
  • Edited By: Bronwyn Harris
  • Last Modified Date: 15 October 2019
  • Copyright Protected:
    Conjecture Corporation
  • Print this Article
Free Widgets for your Site/Blog
Google recognizes a unit of measure called a smoot, which is equal to 5'7", the height of MIT alum Oliver Smoot.  more...

November 15 ,  1867 :  The world's first stock ticker debuted in New York City.  more...

Knowledge extraction is the process of making use of various sources of information to create a cohesive knowledge bank. As part of this approach, the extraction will often draw upon a range of both structured and unstructured sources. When successful, the knowledge extraction results in solid data that can easily be read and interpreted by a given program, allowing the end user to utilize that formal knowledge for whatever purpose he or she desires.

Several different sources may be utilized in the process of knowledge extraction. Within the scope of structured sources, data may be extracted from various types of relational databases or some type of extensible markup language or XML source. Unstructured sources, such as images, different forms of word processing documents, spreadsheets and even text captured on notepad style programs may be utilized as part of the extraction process. As long as the sources are readable to the program being used to manage the knowledge extraction process, they can be used as sources that expand the potential for the project that is being advanced by means of the extraction and allow the final knowledge produced to be usable.


There are several common applications that occur with knowledge extraction. One frequent example is the ability to capture data from an unstructured source and incorporate into some type of structured knowledge source. Extracting data found in relational databases and using it to create new documents, or make use of electronic documents to import data into relational databases, is another example of how this type of extraction can expedite the sharing of formal knowledge without the need to manually enter data that is already available from some other source. This reuse of existing knowledge in some new format is often very helpful in a number of scenarios, making it possible to utilize that knowledge in ways that may not have been possible with the existing source. In this manner, the user can create sources that are ideal for a number of different applications rather than just those relevant to the original home of the formal knowledge.

With the use of data extraction, it is possible to make use of a vast data warehouse, easily importing and exporting data as a way of creating some new source that is usable for a specific purpose. These newly created sources in turn also find a place in the data warehouse and can eventually be used in the creation of new extractions that are used to meet newer usage needs. With this in mind, knowledge extraction can be viewed as a very helpful tool that aids in making the most of all resources currently on hand, simplifying many of the tasks involved with the sharing of that formal knowledge.


You might also Like


Discuss this Article

Post your comments

Post Anonymously


forgot password?