-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathindex.html
More file actions
81 lines (66 loc) · 2.41 KB
/
index.html
File metadata and controls
81 lines (66 loc) · 2.41 KB
1
<html><head><meta name="GENERATOR" content="Microsoft FrontPage 6.0"><meta name="ProgId" content="FrontPage.Editor.Document"><meta http-equiv="Content-Type" content="text/html; charset=windows-1252"><title>KLPP on Github</title></head><body><hr width="90%"><div align="center"><h1><b><i>KLPP on Github</i></b></h1><p><font size="4" face="tahoma">This page contains a list of artifacts developed by the Kurdish Language Processing Project (KLPP) team members.For more information about KLPP, see:<br/><br/><a href="http://eng.uok.ac.ir/esmaili/research/klpp/en/main.htm">http://eng.uok.ac.ir/esmaili/research/klpp/en/main.htm</a></font><br/></p></div><hr width="90%"><blockquote> <h3><font color="#2f1661"><a name="RIs"><font size="4" face="tahoma"> Pewan: The Kurdish Text Corpus / Test Collection </font></a></font></h3> <font size="3" face="tahoma"> <p><a href="https://github.com/klpp/pewan/">Pewan</a> contains a large text corpus (115,000+ Sorani and 25,000+ Kurmanji news articles), 22 queries (in Sorani, Kurmanji, Persian, and English) and their corresponding relevance judgments. Two lists of stopwords (one Sorani, one Kurmanji) are also included. <br/><br/>Get Pewan's mirrored copy from <a href="https://dl.dropbox.com/u/10883132/Pewan.zip">Dropbox</a>.</p></font></blockquote><hr width="90%"><blockquote> <h3><font color="#2f1661"><a name="RIs"><font size="4" face="tahoma"> Kurdish Stemmers </font></a></font></h3> <font size="3" face="tahoma"> <p> We have developed two stemmers for both dialects of the Kurdish language (Sorani and Kurmanji): <ul> <li>Jedar: a new rule-based stemmer which uses a list of Kurdish suffixes</li> <li>GRAS: an implementation of a state-of-the-art statistical stemmer, proposed by J. H. Paik et al. in 2011.</li> </ul> The Java source code for these stemmers can be obtained from <a href="https://github.com/klpp/codes/tree/master/stemming">here</a>. <br/> <br/> </p> </font></blockquote><hr width="90%"><blockquote> <h3><font color="#2f1661"><a name="RIs"><font size="4" face="tahoma"> Kurdish Keyboard Layouts (for Windows and Macintosh) </font></a></font></h3> <font size="3" face="tahoma"> <ul> <li> <a href="hejar.html"> Hejar, </a> Arabic/Persian-based, for Sorani </li> <li> <a href="bedirxan.html">Bedirxan, </a> Latin-based, for Kurmanji </li></ul></font></blockquote><hr width="90%"></body></html>