Clayton Darwin's NLP-Prolog-CGI Page
Hosted by the UGA Artificial Intelligence Center

Note: As always, I'm revising everything, so be patient and overlook all the errors, even the misspellings. I'll get it all right next year.

Today's Menu:

1. SPARSE II: This is a web version of SPARSE II, a parsing program intended to be used as a pedagogical tool to help syntax students grasp the complexity of natural-language grammars and begin to develop their own models. It provides a true introduction to Natural Language Processing without requiring familiarity with Lisp or Prolog. With SPARSE II, grammar rules are supplied by the user rather than being integrated into the program, and there is no underlying theoretical model. SPARSE II simply parses what it can with the rules available. The user is free to implement the rules as needed. The parse algorithm used by SPARSE II returns all possible parses (the web version is limited to 10); handles left recursion, optional elements and null constituents; provides feature unification; and displays parse trees. SPARSE II can be downloaded for use offline.

2. LEXIGRAPH TTR: The LEXIGRAPH TTR transcript analysis program is an experimental forensic tool for marking areas of a transcript which contain abnormal complications compared to the whole. These types of abnormalities in court testimony have been implicated as measures of veracity (or lack of such in this case). The LEXIGRAPH TTR program takes text (a testimony transcript) as input and returns the same text with "abnormal" areas marked.

This site uses SPARSE II CGI scripts written in SWI Prolog by Clayton M. Darwin
and is made available courtesy of the University of Georgia AI Center.