Probabilistic Parsing

Overview

Probabilistic parsing is using dynamic programming algorithms to compute the most likely parse(s) of a given sentence, given a statistical model of the syntactic structure of a language. Research at Stanford has focused on improving the statistical models used as well as the algorithms. Models have been developed for parsing in several languages other than English, including Chinese, Arabic, and German.

People

Software

A java implementation of The Stanford Parser (the parse model which is the basis of much of our work) is available online.