edu.nyu.jet.ne

Class NameAnnotator

java.lang.Object

edu.nyu.jet.ne.NameAnnotator

public class NameAnnotator
extends Object

NameAnnotator provides methods for (extended) named entity annotation based on a dictionary and rules.

Author:

Akira Oda

Constructor Summary

Constructors

Constructor and Description
NameAnnotator() create a new NameAnnotator.

Method Summary

Methods

Modifier and Type	Method and Description
void	annotate(Document doc) annotate document doc with named entity (ENAMEX) annotations using the dictionary and rules of the ENE tagger.
void	annotate(Document doc, Span span) annotate the text in span with named entity (ENAMEX) annotations using the dictionary and rules of the ENE tagger.
void	loadClassDictionary(File file) load the the dictionary to be used by word class tagger.
void	loadClassDictionary(Reader in) load the the dictionary to be used by word class tagger.
void	loadClassHierarchy(File file)
void	loadRules(File file) load the rules to be used by the ENE tagger using Reader 'in'.
void	loadRules(Reader in) load the rules to be used by the ENE tagger using Reader 'in'.
void	setAliasMap(Map<String,String> map) specify a mapping to be used to translate the TYPE feature of ENAMEX annotations as a final step in tagging.
void	setDictionary(Dictionary dict) specify the dictionary to be used by the ENE tagger.

Methods inherited from class java.lang.Object

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

Constructor Detail

NameAnnotator

public NameAnnotator()

create a new NameAnnotator.

Method Detail

setDictionary

public void setDictionary(Dictionary dict)

specify the dictionary to be used by the ENE tagger.

loadClassDictionary

public void loadClassDictionary(Reader in)
                         throws IOException

load the the dictionary to be used by word class tagger.

Throws:

IOException

loadClassDictionary

public void loadClassDictionary(File file)
                         throws IOException

load the the dictionary to be used by word class tagger.

Throws:

IOException

loadRules

public void loadRules(Reader in)
               throws IOException,
                      RuleFormatException

load the rules to be used by the ENE tagger using Reader 'in'.

Throws:

IOException

RuleFormatException

loadRules

public void loadRules(File file)
               throws IOException,
                      RuleFormatException

load the rules to be used by the ENE tagger using Reader 'in'.

Throws:

IOException

RuleFormatException

annotate

public void annotate(Document doc,
            Span span)

annotate the text in span with named entity (ENAMEX) annotations using the dictionary and rules of the ENE tagger. If an alias map has been specified by 'setAliasMap', the tags are translated using this map.

annotate

public void annotate(Document doc)

annotate document doc with named entity (ENAMEX) annotations using the dictionary and rules of the ENE tagger. If an alias map has been specified by 'setAliasMap', the tags are translated using this map.

setAliasMap

public void setAliasMap(Map<String,String> map)

specify a mapping to be used to translate the TYPE feature of ENAMEX annotations as a final step in tagging.

loadClassHierarchy

public void loadClassHierarchy(File file)
                        throws IOException

Throws:

IOException