I am currently working with Dr. Ted Pedersen on Text-NSP. Text-NSP allows users to count sequences of Ngrams in large corpora of text, and measure their association. As part of the project, I am rewriting the Text-NSP using Object Oriented Perl. The future work includes writing new measures of association, extending the existing measures to handle trigrams, adding capabilities to count Ngrams directly from the World Wide Web. For more information about Text-NSP please visit http://ngram.sourceforge.net
You can download the current official release of Text-NSP here.
You can also view the latest source code of Text-NSP here.
The aim of the project was to develop a system to score student essays based on various features such as relevance, grammar and proper statement of facts. I was involved in the relevance measure, semantic gibberish detection, scoring and the web interface. Visit WebGrader homepage http://indautograder.sourceforge.net for further details.
You can download the current official release of WebGrader here.
WordNet-Similiarity-Visual is a graphical extension for WordNet::Similarity. It provides a gui for WordNet::Similarity and visualization tools for the various edge counting measures like path, wup, lch and hso. This project is available under CPAN.
You can download the current official release of WordNet-Similarity-Visual from here.