Report:VantagePoint/Text Mining and Clustering/Natural Language Processing

From Intellogist

Jump to: navigation, search
  Report          
This report was created by the Intellogist Team and is available for viewing only. If you'd like to share your knowledge on Intellogist, please visit the Best Practices, Glossary, or Community Reports pages. If you are a registered user and would like to be notified of any substantial changes to this report, you may place a "watch" on the Revisions page, which is the last page listed on the table of contents. To learn more about using the Intellogist "watchlist," see the Watchlist Help page.

Natural Language Processing

VantagePoint is able to run natural language processing (NLP) on any free text such as a title or an abstract. NLP processing occurs most often by importing data or by running the Extract Nearby Phrases command.

An Import Filter associated with the search system from which data is being imported will determine if NLP is used, as well as what fields will receive processing. For example, the PatBase Import Filter finds the title, abstract, and claims fields and uses the NLP processor to determine the NLP phrases for each field. Most Import Filters use NLP on at least one field; if NLP is not activated in a particular filter, users have to manually add NLP with the Import Filter Editor. Using the Import Filter Editor, users can make changes to when and how NLP is used.


The VantagePoint import filter can apply natural language processing to data during the import process. Most filters use NLP processing at some point; those that do not would have to be manually edited to include NLP.


The Extract Nearby Phrases command is found in the Fields menu (in the figure above, it applies specifically to patent text fields such as abstract and claims sections). These commands allow users to extract NLP phrases from a specific free text field using the terms contained in a group (the group can be a list or a user-defined group) as a point of reference. In the example below, the user created a group based upon the term "sensors." The NLP processor will look through all the documents in that group to determine a set of target terms that are prevalent throughout said documents. The NLP processor will then apply the target terms throughout the free text field (in this case, the abstract), to look for the terms and adjacent words in order to create a list of phrases.


Users select a group containing the target terms of interest for use as a point of reference. These target terms will then be applied to a free text field to create NLP phrases.


The image below shows an example of a few of the phrases created by this process.


Some example phrases extracted by Natural Language Processing are shown.
Patent search questions. Expert answers.  Brought to you by Landon IP
HOT Items

Intellogist is brought to you by the patent search experts at Landon IP.

Welcome to Intellogist!

To network with our international community of patent info pros, please create an account.

For a list of our current members, see our Community Page.