public Pipe buildPipe() {
ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
pipeList.add(new Input2CharSequence("UTF-8"));
Pattern tokenPattern = Pattern.compile("[\\p{L}\\p{N}_]+");
pipeList.add(new CharSequence2TokenSequence(tokenPattern));
pipeList.add(new TokenSequenceRemoveStopwords(false, false));
pipeList.add(new TokenSequence2FeatureSequence());
// pipeList.add(new FeatureSequence2FeatureVector());
// pipeList.add(new PrintInputAndTarget());
SerialPipes serialPipeList = new SerialPipes(pipeList);
serialPipeList.setDataAlphabet(alphabet);
return serialPipeList;
}
public void setPreTagger(banner.tagging.Tagger preTagger) {
((Pretagger) pipe.getPipe(2)).setPreTagger(preTagger);
}
public void setPosTagger(dragon.nlp.tool.Tagger posTagger) {
((LemmaPOS) pipe.getPipe(1)).setPosTagger(posTagger);
}
public void setLemmatiser(Lemmatiser lemmatiser) {
((LemmaPOS) pipe.getPipe(1)).setLemmatiser(lemmatiser);
}