public class EngWordPairIndexer extends Object implements WordPairIndexer
Indexer for word pair
Copyright: Copyright (c) 2005
Company: IST, Drexel University
| Modifier and Type | Field and Description |
|---|---|
protected IntSuperSparseMatrix[] |
arrPairSentLeftMatrix |
protected IntSuperSparseMatrix[] |
arrPairSentRightMatrix |
protected SimpleElementList |
docKeyList |
protected int |
flushInterval |
protected int |
indexedNum |
protected Lemmatiser |
lemmatiser |
protected int |
maxSpan |
protected WordPairGenerator |
pairGenerator |
protected SimplePairList |
pairKeyList |
protected DocumentParser |
parser |
protected SentenceBase |
sentenceBase |
protected Tagger |
tagger |
protected SimpleElementList |
wordKeyList |
protected WordPairStatList |
wordpairStatList |
| Constructor and Description |
|---|
EngWordPairIndexer(String folder,
int maxSpan,
Tagger tagger,
Lemmatiser lemmatiser) |
EngWordPairIndexer(String folder,
int maxSpan,
Tagger tagger,
Lemmatiser lemmatiser,
WordPairGenerator pairGenerator) |
| Modifier and Type | Method and Description |
|---|---|
void |
close() |
void |
flush() |
DocumentParser |
getDocumentParser() |
void |
index(CollectionReader collectionReader) |
boolean |
indexArticle(Article curArticle) |
protected void |
preprocessSentence(Sentence sent)
Preprocess a sentence including tagging, lemmatising and indexing.
|
void |
setDocumentParser(DocumentParser parser) |
protected int maxSpan
protected Tagger tagger
protected Lemmatiser lemmatiser
protected WordPairGenerator pairGenerator
protected SentenceBase sentenceBase
protected IntSuperSparseMatrix[] arrPairSentLeftMatrix
protected IntSuperSparseMatrix[] arrPairSentRightMatrix
protected SimpleElementList docKeyList
protected SimpleElementList wordKeyList
protected SimplePairList pairKeyList
protected WordPairStatList wordpairStatList
protected DocumentParser parser
protected int flushInterval
protected int indexedNum
public EngWordPairIndexer(String folder, int maxSpan, Tagger tagger, Lemmatiser lemmatiser)
public EngWordPairIndexer(String folder, int maxSpan, Tagger tagger, Lemmatiser lemmatiser, WordPairGenerator pairGenerator)
public DocumentParser getDocumentParser()
getDocumentParser in interface WordPairIndexerpublic void setDocumentParser(DocumentParser parser)
setDocumentParser in interface WordPairIndexerpublic void close()
close in interface WordPairIndexerpublic void flush()
flush in interface WordPairIndexerpublic void index(CollectionReader collectionReader)
index in interface WordPairIndexerpublic boolean indexArticle(Article curArticle)
indexArticle in interface WordPairIndexerprotected void preprocessSentence(Sentence sent)
sent - the sentence for preprocessingCopyright © 2018 JULIE Lab, Germany. All rights reserved.