Skip to content

Commit

Permalink
Update README.MD
Browse files Browse the repository at this point in the history
  • Loading branch information
electronart committed Mar 17, 2019
1 parent a20a7c7 commit f4e080e
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion docs/README.MD
Expand Up @@ -5,7 +5,7 @@ WELCOME! .
Please read the LICENSE.TXT and other docs in the /docs folder.

## What is it for?
Primarily it was developed to assist optimizing stemming rules in various languages and for comparing stemmers. It compares two word lists of the same length, these are normally the input and out of a stemmer. It could however be useful for other purposes. It displays the input and output lists with measures of similarity and difference and calculates useful measures of stemmer strength, under and over stemming counts, and error rate relative to truncation (ERRT) according to the method described by Chris D Paice of Lancaster University. (Chris Paice. 'Method for Evaluation of Stemming Algorithms Based on Error Counting': http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.89.9560&rep=rep1&type=pdf
Primarily it was developed to assist optimizing stemming rules in various languages and for comparing stemmers. It compares two word lists of the same length, these are normally the input and out of a stemmer. It could however be useful for other purposes. It displays the input and output lists with measures of similarity and difference and calculates useful measures of stemmer strength, under and over stemming counts, and error rate relative to truncation (ERRT) according to the method described by Chris D Paice of Lancaster University. (Chris Paice. 'Method for Evaluation of Stemming Algorithms Based on Error Counting': http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.89.9560&rep=rep1&type=pdf ).

## HISTORY
Word List Analyzer started life for internal use while developing stemming rules for various languages for the dtSearch Engine, it was released in 2013 (as List Analyser 1.0 'beta' ) to customers of dtSearch Corp, 'dtSearch UK' and academic users free of charge; it is a single executable written in C# (originally using the Open Source IDE SharpDevelop. http://www.icsharpcode.net/ ). The last update was in 2016 (1.1.5876 beta) which added Error Rate Relative to Truncation (ERRT), a method devised by Chris Paice of Lancaster University. The December 2018 Release build on GitHub v1.1.6916 was a rebuild using Visual Studio 2017, no major code changes. Stemming Tester 1.4 executable (no source) for use with the List Analyzer (see https://www.dtsearch.co.uk/products/stemming-tester.aspx ) was added to the Release build in March 2019.
Expand Down

0 comments on commit f4e080e

Please sign in to comment.