Disclaimer:
This page is my current project,
and as such, is very much under construction.
My Interests
I am beginning to believe that given enough time, my interests might
entirely change, though for right now, here are some of the areas that
I am interested in.
|
|
Text Summarization | Text Generation |
Document Categorization | Keyword Extraction |
|
|
|
Computational
Linguistics
Text Generation
In
short this is the process of automatically generating text documents of
various types from some sort of knowledge.
Often times this takes the
form of giving a computer a knowledge base, containing knowledge about
a specific type subject, and then the program is required to generate a
natural language text from that knowledge. My personal experience
has been in genenerating web pages from a knowledge base containing knowledge
and ways of putting together that knowledge to produce client pages with
a minimal amount of human interaction.
The internet has brought about many things. One of those things is the massive amount of data that many people now find themselves trying to sort through in order to find out about something very specific. Unfortunately, sometimes the web search engines that are most often employed by these individuals become overrun by individuals trying to sell their products at any cost, and sometimes will even resort to tactics which will get them listed in completely irrelevant searches, just to try and make a buck. This particular field looks at things from the pure direction of information. We beileve that a person is looking for a certain piece of information and therefore wish to make it easier to get to that information. This field's main relevance is to large collections of documents, such as one would find in a repository