<?xml version="1.0" encoding="UTF-8"?>
<posts update='2008-10-06 18:46:07' user=""><post 
   href="http://java-source.net/open-source/html-parsers" 
   description="Open Source HTML Parsers in Java" 
   
   hash="d0affdbb6c5b6e03d1268050ad93b997"
   user="sb3000"
   tag="html java parser software text-mining "
   time="2007-05-25T18:12:18+0200" />
<post 
   href="http://jtidy.sourceforge.net/" 
   description="JTidy - JTidy" 
   
   hash="690cce6426dc0a0d53de127a03dbb86a"
   user="sb3000"
   tag="html java software text-mining "
   time="2007-05-25T18:09:48+0200" />
<post 
   href="http://www.comp.nus.edu.sg/~rpnlpir/downloads/corpora/smsCorpus/" 
   description="README for the NUS SMS Corpus" 
   
   hash="dd32a969e76222c6adb539b7a92929e8"
   user="sb3000"
   tag="sms text-mining "
   time="2007-03-23T14:55:19+0100" />
<post 
   href="http://secondstring.sourceforge.net/" 
   description="SecondString Project Page" 
   
   hash="c85ab1d2d95f82564d8a3e2c7bbb008b"
   user="sb3000"
   tag="similarity text-mining "
   time="2006-10-09T00:27:03+0200" />
<post 
   href="http://www.dcs.shef.ac.uk/~sam/simmetrics.html" 
   description="SimMetrics - open source Similarity Measure Library" 
   
   hash="7a22de4888d6bab1d0a08250f66d3523"
   user="sb3000"
   tag="similarity text-mining "
   time="2006-10-09T00:24:19+0200" />
<post 
   href="http://kt.ijs.si/Dunja/TextGarden/" 
   description="Text-Garden -- Text-Mining Software Tools" 
   
   hash="400802eed594209f6754c49420312ca2"
   user="sb3000"
   tag="ml sekt text-mining toolkit "
   time="2006-08-23T16:07:22+0200" />
<post 
   href="http://trec.nist.gov/data/t2001_filtering.html" 
   description="Text REtrieval Conference (TREC) TREC 2001 Filtering Track Collections" 
   
   hash="a1a8b8c4a8d0639a6757f9175fb898b4"
   user="sb3000"
   tag="corpus text-mining "
   time="2006-04-21T15:02:35+0200" />
<post 
   href="http://alg.ncsa.uiuc.edu/do/tools/t2k" 
   description="T2K (Text to Knowledge)" 
   
   hash="aee1ae7dbebb055d345dc68d87a47929"
   user="sb3000"
   tag="ml text-mining tool "
   time="2006-04-21T14:58:04+0200" />
<post 
   href="http://www.ai.mit.edu/projects/jmlr/papers/volume5/lewis04a/lyrl2004_rcv1v2_README.htm" 
   description="RCV1" 
   
   hash="370359bb3048a436402f2051fd850c34"
   user="sb3000"
   tag="corpus text-mining "
   time="2006-04-21T14:57:56+0200" />
<post 
   href="http://trec.nist.gov/data/reuters/reuters.html" 
   description="Reuters Corpora @ NIST" 
   
   hash="d15d7cee47d8a0b288b331edbbabd8f2"
   user="sb3000"
   tag="corpus text-mining "
   time="2006-04-21T14:57:49+0200" />
</posts>
