public class DictionaryTagger extends Object implements Tagger
| Modifier and Type | Field and Description |
|---|---|
protected Trie<String,Set<EntityType>> |
entities |
protected Trie<String,Boolean> |
notInclude |
| Constructor and Description |
|---|
DictionaryTagger()
Creates a new
DictionaryTagger |
| Modifier and Type | Method and Description |
|---|---|
boolean |
add(List<String> tokens,
Collection<EntityType> types) |
void |
add(String text,
Collection<EntityType> types) |
void |
add(String text,
EntityType type)
Adds a single entry to the dictionary.
|
void |
configure(org.apache.commons.configuration.HierarchicalConfiguration config,
Tokenizer tokenizer) |
Tokenizer |
getTokenizer() |
boolean |
isDropEndParentheticals() |
boolean |
isFilterContainedMentions() |
boolean |
isGenerate2PartVariations() |
boolean |
isNormalizeDigits() |
boolean |
isNormalizeMixedCase() |
void |
load(org.apache.commons.configuration.HierarchicalConfiguration config) |
protected List<String> |
process(String input) |
void |
setDropEndParentheticals(boolean dropEndParentheticals) |
void |
setFilterContainedMentions(boolean filterContainedMentions) |
void |
setGenerate2PartVariations(boolean generate2PartVariations) |
void |
setNormalizeDigits(boolean normalizeDigits) |
void |
setNormalizeMixedCase(boolean normalizeMixedCase) |
void |
setTokenizer(Tokenizer tokenizer) |
int |
size() |
void |
suppress(String text) |
void |
tag(Sentence sentence)
|
protected String |
transform(String str) |
protected Trie<String,Set<EntityType>> entities
public DictionaryTagger()
DictionaryTaggerpublic void configure(org.apache.commons.configuration.HierarchicalConfiguration config,
Tokenizer tokenizer)
public void load(org.apache.commons.configuration.HierarchicalConfiguration config)
throws IOException
IOExceptionpublic void add(String text, EntityType type)
text - The text to findtype - The EntityType to tag the text withpublic void add(String text, Collection<EntityType> types)
public boolean add(List<String> tokens, Collection<EntityType> types)
public void suppress(String text)
public int size()
public Tokenizer getTokenizer()
public void setTokenizer(Tokenizer tokenizer)
public boolean isFilterContainedMentions()
public void setFilterContainedMentions(boolean filterContainedMentions)
public boolean isNormalizeMixedCase()
public void setNormalizeMixedCase(boolean normalizeMixedCase)
public boolean isNormalizeDigits()
public void setNormalizeDigits(boolean normalizeDigits)
public boolean isGenerate2PartVariations()
public void setGenerate2PartVariations(boolean generate2PartVariations)
public boolean isDropEndParentheticals()
public void setDropEndParentheticals(boolean dropEndParentheticals)
Copyright © 2018 JULIE Lab, Germany. All rights reserved.