Description: tf-idf program, friends wrote, very good. Similarity calculation for Chinese sentences, the sentence weights are calculated, sort, twenty-two similarity between sub-calculation. A corpus, can be run directly
File list (Check if you may need any files):
IDFCal\.classpath
......\.project
......\.settings\org.eclipse.jdt.core.prefs
......\bin\DocItem.class
......\...\IDFCal.class
......\...\ScoreCompare.class
......\...\Term.class
......\...\WordFilter.class
......\data.txt
......\src\DocItem.java
......\...\IDFCal.java
......\...\ScoreCompare.java
......\...\Term.java
......\...\WordFilter.java
......\.settings
......\bin
......\lib
......\src
IDFCal