Natural Language Processing (NLP) Demos (Cognitive Computation Group, University of Illinois at Urbana-Champaign)
From the webpage:
Most of the information available today is in free form text. Current technologies (google, yahoo) allow us to access text only via key-word search.
We would like to facilitate content-based access to information. Examples include:
- Topical and Functional categorization of documents: Find documents that deal with stem cell research, but only Call for Proposals.
- Semantic categorization: Find documents about Columbus (the City, not the Person).
- Retrieval of concepts and entities rather than strings in text: Find documents about JFK, the president; include those documents that mention him as “John F. Kennedy, John Kennedy, Congressman Kennedy or any other possible writing; but not those that mention the baseball player John Kennedy, nor any of JFK’s relatives.
- Extraction of information based on semantic categorization: Find a list of all companies that participated in merges in the last year. List all professors in Illinois that do research in Machine Learning.
I count twenty (20) separate demos.
Gives you a good sense of the current state of NLP.
I first saw this at: Demos of NLP by Ryan Swanstrom.