com.hankcs.hanlp.model.perceptron

Class PerceptronLexicalAnalyzer

java.lang.Object

com.hankcs.hanlp.seg.Segment

com.hankcs.hanlp.seg.CharacterBasedSegment

com.hankcs.hanlp.tokenizer.lexical.AbstractLexicalAnalyzer

com.hankcs.hanlp.model.perceptron.PerceptronLexicalAnalyzer

All Implemented Interfaces:

LexicalAnalyzer, NERecognizer, POSTagger, Segmenter

public class PerceptronLexicalAnalyzer
extends AbstractLexicalAnalyzer

感知机词法分析器，支持简繁全半角和大小写

Author:

hankcs

Field Summary

Fields inherited from class com.hankcs.hanlp.tokenizer.lexical.AbstractLexicalAnalyzer

enableRuleBasedSegment, neRecognizer, posTagger, segmenter, typeTable

Fields inherited from class com.hankcs.hanlp.seg.Segment

config, customDictionary

Constructor Summary

Constructors

Constructor and Description
PerceptronLexicalAnalyzer() 加载配置文件指定的模型构造词法分析器
PerceptronLexicalAnalyzer(LinearModel CWSModel)
PerceptronLexicalAnalyzer(LinearModel cwsModel, LinearModel posModel, LinearModel nerModel)
PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter)
PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter, PerceptronPOSTagger posTagger)
PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter, PerceptronPOSTagger posTagger, PerceptronNERecognizer neRecognizer)
PerceptronLexicalAnalyzer(String cwsModelFile)
PerceptronLexicalAnalyzer(String cwsModelFile, String posModelFile)
PerceptronLexicalAnalyzer(String cwsModelFile, String posModelFile, String nerModelFile)

Method Summary

Modifier and Type	Method and Description
PerceptronNERecognizer	getPerceptionNERecognizer() 获取命名实体识别器
PerceptronPOSTagger	getPerceptronPOSTagger() 获取词性标注器
PerceptronSegmenter	getPerceptronSegmenter() 获取分词器
boolean	learn(Sentence sentence) 在线学习
boolean	learn(String segmentedTaggedSentence) 在线学习
String[]	namedEntityRecognize(String[] wordArray, String[] posArray) 命名实体识别
String[]	partOfSpeechTag(List<String> wordList) 词性标注
void	segment(String text, List<String> output) 中文分词

Methods inherited from class com.hankcs.hanlp.tokenizer.lexical.AbstractLexicalAnalyzer

acceptCustomWord, analyze, combineWithCustomDictionary, enableRuleBasedSegment, getNERTagSet, recognize, roughSegSentence, segment, segment, segment, segment, segmentAfterRule, segSentence, tag, tag

Methods inherited from class com.hankcs.hanlp.seg.CharacterBasedSegment

guessAttribute, toVertexList

Methods inherited from class com.hankcs.hanlp.seg.Segment

atomSegment, combineByCustomDictionary, combineByCustomDictionary, combineByCustomDictionary, combineByCustomDictionary, convert, enableAllNamedEntityRecognize, enableCustomDictionary, enableCustomDictionary, enableCustomDictionaryForcing, enableIndexMode, enableIndexMode, enableJapaneseNameRecognize, enableMultithreading, enableMultithreading, enableNameRecognize, enableNumberQuantifierRecognize, enableOffset, enableOrganizationRecognize, enablePartOfSpeechTagging, enablePlaceRecognize, enableTranslatedNameRecognize, mergeNumberQuantifier, quickAtomSegment, seg, seg, seg2sentence, seg2sentence, simpleAtomSegment

Methods inherited from class java.lang.Object

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

Constructor Detail

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter)

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter,
                                 PerceptronPOSTagger posTagger)

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(PerceptronSegmenter segmenter,
                                 PerceptronPOSTagger posTagger,
                                 PerceptronNERecognizer neRecognizer)

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(LinearModel cwsModel,
                                 LinearModel posModel,
                                 LinearModel nerModel)

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(String cwsModelFile,
                                 String posModelFile,
                                 String nerModelFile)
                          throws IOException

Throws:

IOException

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(String cwsModelFile,
                                 String posModelFile)
                          throws IOException

Throws:

IOException

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(String cwsModelFile)
                          throws IOException

Throws:

IOException

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer(LinearModel CWSModel)

PerceptronLexicalAnalyzer

public PerceptronLexicalAnalyzer()
                          throws IOException

加载配置文件指定的模型构造词法分析器

Throws:

IOException

Method Detail

segment

public void segment(String text,
                    List<String> output)

中文分词

Parameters:

text -

output -

partOfSpeechTag

public String[] partOfSpeechTag(List<String> wordList)

词性标注

Parameters:

wordList -

Returns:

namedEntityRecognize

public String[] namedEntityRecognize(String[] wordArray,
                                     String[] posArray)

命名实体识别

Parameters:

wordArray -

posArray -

Returns:

learn

public boolean learn(String segmentedTaggedSentence)

在线学习

Parameters:

segmentedTaggedSentence - 已分词、标好词性和命名实体的人民日报2014格式的句子

Returns:

是否学习成果（失败的原因是句子格式不合法）

learn

public boolean learn(Sentence sentence)

在线学习

Parameters:

sentence - 已分词、标好词性和命名实体的人民日报2014格式的句子

Returns:

是否学习成果（失败的原因是句子格式不合法）

getPerceptronSegmenter

public PerceptronSegmenter getPerceptronSegmenter()

获取分词器

Returns:

getPerceptronPOSTagger

public PerceptronPOSTagger getPerceptronPOSTagger()

获取词性标注器

Returns:

getPerceptionNERecognizer

public PerceptronNERecognizer getPerceptionNERecognizer()

获取命名实体识别器

Returns: