public class LingPipeNer extends TrainableNamedEntityRecognizer
This class wraps the LingPipe implementation of a Named Entity Recognizer. We wrapped the slowest but most accurate recognizer (CharLmRescoringChunker) since we are interested in the best possible results. LingPipe uses a "long-distance character language model-based chunker that operates by rescoring the output of a contained character language model HMM chunker.
| Constructor and Description |
|---|
LingPipeNer() |
| Modifier and Type | Method and Description |
|---|---|
List<Annotation> |
getAnnotations(String inputText) |
String |
getModelFileEnding() |
String |
getName() |
boolean |
loadModel(String configModelFilePath) |
static void |
main(String[] args) |
boolean |
setsModelFileEndingAutomatically() |
boolean |
train(String trainingFilePath,
String modelFilePath) |
getModelFileEndingIfNotSetAutomatically, oneModelPerConcept, train, trainevaluate, evaluate, evaluate, evaluate, getTaggingFormat, setTaggingFormat, tagpublic String getModelFileEnding()
getModelFileEnding in class TrainableNamedEntityRecognizerpublic boolean setsModelFileEndingAutomatically()
setsModelFileEndingAutomatically in class TrainableNamedEntityRecognizerpublic boolean train(String trainingFilePath, String modelFilePath)
train in class TrainableNamedEntityRecognizerpublic boolean loadModel(String configModelFilePath)
loadModel in class TrainableNamedEntityRecognizerpublic List<Annotation> getAnnotations(String inputText)
getAnnotations in interface TaggergetAnnotations in class NamedEntityRecognizerpublic String getName()
getName in class NamedEntityRecognizerpublic static void main(String[] args)
Copyright © 2018. All rights reserved.