Read The
Web - Resource List
The first round projects made use of various software tools, lists and
libraries. Let's gather those and more into a list of candidate
resources for our next system.
Please add to this list by editing this page, which is at /afs/cs/project/theo-21/www/resources.html.
Software systems to consider:
- Brill's part-of-speech tagger, or Etzioni's simplification of it
- Lemur/Indri IR engine: Lemur Website
- LingPipe is one of many packages that provides simple sentence-chunking, POS tagging, NE recognition.
- ...
Libraries, lexicons, etc.:
- Wordnet (available at http://wordnet.princeton.edu/ )
- Gazetteers, such as the one Eric Nyberg has? Will be useful component of NER for locations.
- ...
This page is located in the file
/afs/cs/project/theo-21/www/resources.html.
It is writable by any member of the course.
It was created using NVU, freely available at http://www.nvu.com/