NameRecognizer.java

package edu.northwestern.at.utils.corpuslinguistics.namerecognizer;

/*	Please see the license information at the end of this file. */

import java.io.*;
import java.net.*;
import java.util.*;

import edu.northwestern.at.utils.*;
import edu.northwestern.at.utils.corpuslinguistics.adornedword.*;
import edu.northwestern.at.utils.corpuslinguistics.lexicon.*;
import edu.northwestern.at.utils.corpuslinguistics.postagger.*;

import edu.northwestern.at.morphadorner.tools.*;

/**	Interface for a Name Recognizer.
 */

public interface NameRecognizer
{
	/**	Get the lexicon.
	 *
	 *	@return		The lexicon.	May be null if name recognizer does not
	 *								use a lexicon.
	 */

	public Lexicon getLexicon();

	/**	Set the lexicon.
	 *
	 *	@param	lexicon		Lexicon used for name recognition.
	 */

	public void setLexicon( Lexicon lexicon );

	/**	Get part of speech tagger.
	 *
	 *	@return		The part of speech tagger.
	 *
	 */

	public PartOfSpeechTagger getPartOfSpeechTagger();

	/**	Set part of speech tagger.
	 *
	 *	@param	partOfSpeechTagger	The part of speech tagger.
	 *
	 */

	public void setPartOfSpeechTagger
	(
		PartOfSpeechTagger partOfSpeechTagger
	);

	/**	Returns names from text.
	 *
	 *	@param	text	The text from which to extract names.
	 *
	 *	@return			Array of string sets containing names and places.
	 *					[0]	= Set of proper names.
	 *					[1]	= Set of places.
	 */

	 public Set<String>[] findNames( String text );

	/**	Returns names from list of adorned word sentences.
	 *
	 *	@param	sentences	The list of sentences of adorned words
	 *						from which to extract names.
	 *
	 *	@return				Array of string sets containing names and places.
	 *						[0]	= Set of proper names.
	 *						[1]	= Set of places.
	 */

	public <T extends AdornedWord> Set<String>[] findNames
	(
		List<List<T>> sentences
	);

	/**	Returns name positions in list of adorned word sentences.
	 *
	 *	@param	sentences	The list of sentences of adorned words
	 *						from which to extract names.
	 *
	 *	@return			Array of Set of names and places.
	 *					[0]	= Set of proper names.
	 *					[1]	= Set of places.
	 */

	public <T extends AdornedWord> List<NamePosition>[] findNamePositions
	(
		List<List<T>> sentences
	);
}

/*
Copyright (c) 2008, 2009 by Northwestern University.
All rights reserved.

Developed by:
   Academic and Research Technologies
   Northwestern University
   http://www.it.northwestern.edu/about/departments/at/

Permission is hereby granted, free of charge, to any person
obtaining a copy of this software and associated documentation
files (the "Software"), to deal with the Software without
restriction, including without limitation the rights to use,
copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following
conditions:

    * Redistributions of source code must retain the above copyright
      notice, this list of conditions and the following disclaimers.

    * Redistributions in binary form must reproduce the above
      copyright notice, this list of conditions and the following
      disclaimers in the documentation and/or other materials provided
      with the distribution.

    * Neither the names of Academic and Research Technologies,
      Northwestern University, nor the names of its contributors may be
      used to endorse or promote products derived from this Software
      without specific prior written permission.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE CONTRIBUTORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS WITH THE SOFTWARE.
*/