/**
* Outputs the settings for this configuration to the console, very useful for ensuring the
* configuration is set as desired prior to a training run
*/
public void log() {
System.out.println(
"Lemmatiser: " + (lemmatiser == null ? null : lemmatiser.getClass().getName()));
System.out.println("POSTagger: " + (posTagger == null ? null : posTagger.getClass().getName()));
System.out.println("Tokenizer: " + tokenizer.getClass().getName());
System.out.println("Tag format: " + tagFormat.name());
System.out.println(
"PostProcessor: " + (postProcessor == null ? null : postProcessor.getClass().getName()));
System.out.println("Using numeric normalization: " + useNumericNormalization);
System.out.println("CRF order is " + order);
System.out.println("Using feature induction: " + useFeatureInduction);
System.out.println("Text textDirection: " + textDirection);
}
protected List<String> process(String input) {
if (input == null) throw new IllegalArgumentException();
List<String> tokens = tokenizer.getTokens(input);
for (int i = 0; i < tokens.size(); i++) tokens.set(i, transform(tokens.get(i)));
return tokens;
}