public class NGramTaggerTrainer
extends java.lang.Object
Modifier and Type | Field and Description |
---|---|
protected static java.lang.String |
sepChars
Separator character(s) for tokens in input text.
|
protected static int |
trainingDataCount
Number of lines/words in training data.
|
protected static java.lang.String |
trainingDataFileName
The input training data file to process.
|
protected static TransitionMatrix |
transitionMatrix
Part of speech transition probability matrix.
|
protected static java.lang.String |
transitionMatrixFileName
Transition matrix file name.
|
protected static Lexicon |
wordLexicon
The word lexicon.
|
Constructor and Description |
---|
NGramTaggerTrainer() |
Modifier and Type | Method and Description |
---|---|
protected static void |
getProgramParameters(java.lang.String[] args)
Get program parameters.
|
protected static java.net.URL |
getURL(java.lang.String fileNameOrURL)
Get URL from file name or URL.
|
protected static void |
help()
Prints the help message.
|
protected static void |
loadTrainingData()
Load training data.
|
static void |
main(java.lang.String[] args)
Create and run a part of speech tagger trainer.
|
protected static Lexicon wordLexicon
protected static java.lang.String trainingDataFileName
protected static int trainingDataCount
protected static TransitionMatrix transitionMatrix
protected static java.lang.String transitionMatrixFileName
protected static java.lang.String sepChars
protected static void getProgramParameters(java.lang.String[] args) throws java.io.IOException
args
- Command line parameters.java.io.IOException
protected static void loadTrainingData() throws java.io.IOException
java.io.IOException
public static void main(java.lang.String[] args)
protected static java.net.URL getURL(java.lang.String fileNameOrURL)
fileNameOrURL
- The file name or URL string.protected static void help()