com.knowledgebooks.nlp
Class KeyPhraseExtractionAndSummary

java.lang.Object
  com.knowledgebooks.nlp.KeyPhraseExtractionAndSummary

public class KeyPhraseExtractionAndSummary
extends java.lang.Object

General NLP utilities for extracting key phrases from input text also generating short summaries of input text.

Copyright 2002-2008 by Mark Watson. All rights reserved.

This software is not public domain. It can be legally used under either of the following licenses:

1. KnowledgeBooks.com Non Commercial Royality Free License
2. KnowledgeBooks.com Commercial Use License

see www.knowledgebooks.com for details

  Class to extract key-word based summarization from text. The algorithm is as follows:

    1. find the most likely topic tags for the text
    2. locate words that contributed to forming these categories and
       set a weighting based on the relevance of the categories
    3. "smudge" out these weightings to surrounding words.
    4. using a threshold cutoff, locate summarization with high weightings
 

Constructor Summary

KeyPhraseExtractionAndSummary(java.lang.String words)

Method Summary

PhraseList	getAllPhrases()
java.lang.String[]	getKeyWords()
int	getNumPhrases()
java.lang.String	getPhrase(int index)
float	getScore(int index)
java.lang.String	getSummary()
static void	main(java.lang.String[] args)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

KeyPhraseExtractionAndSummary

public KeyPhraseExtractionAndSummary(java.lang.String words)

Parameters:

words -

Method Detail

getKeyWords

public java.lang.String[] getKeyWords()

getNumPhrases

public int getNumPhrases()

getScore

public float getScore(int index)

getPhrase

public java.lang.String getPhrase(int index)

getAllPhrases

public PhraseList getAllPhrases()

getSummary

public java.lang.String getSummary()

main

public static void main(java.lang.String[] args)