private static void outputInputRow (PrintWriter out, TokenSequence input, int start, int end) { out.println (" <tr class=\"input\">"); out.println (" <td class=\"label\"></td>"); for (int ip = start; ip < end; ip++) { out.print ("<td>"+input.get(ip).getText()+"</td>"); } out.println (" </tr>"); }
@Override public Instance pipe(Instance inst) { TokenSequence ts = (TokenSequence) inst.getData(); SyllStructure struct = (SyllStructure) ts.getProperty(PhonemeCrfTrainer.PROP_STRUCTURE); checkNotNull(struct, "no sylls", inst); for (int i = 0; i < ts.size(); i++) { Token tok = ts.get(i); tok.setFeatureValue("SYLLCNT_" + struct.getSyllIndexForGraphoneGramIndex(i), 1.0); } return inst; } }
private static void outputInputRow (PrintWriter out, TokenSequence input, int start, int end) { out.println (" <tr class=\"input\">"); out.println (" <td class=\"label\"></td>"); for (int ip = start; ip < end; ip++) { out.print ("<td>"+input.get(ip).getText()+"</td>"); } out.println (" </tr>"); }
public String toString () { StringBuffer sb = new StringBuffer(); sb.append( "TokenSequence " + super.toString() + "\n" ); for (int i = 0; i < this.size(); i++) { String tt = get(i).toString(); sb.append( "Token#" + i + ":" ); sb.append( tt ); if (!tt.endsWith( "\n" )) sb.append( "\n" ); } return sb.toString(); }
public String toString () { StringBuffer sb = new StringBuffer(); sb.append( "TokenSequence " + super.toString() + "\n" ); for (int i = 0; i < this.size(); i++) { String tt = get(i).toString(); sb.append( "Token#" + i + ":" ); sb.append( tt ); if (!tt.endsWith( "\n" )) sb.append( "\n" ); } return sb.toString(); }
public String toStringShort () { StringBuffer sb = new StringBuffer(); for (int i = 0; i < this.size(); i++) { String tt = get(i).toString(); tt.replaceAll("\n",""); if (i > 0){ sb.append(" "); } sb.append(tt); } return sb.toString(); }
public String toStringShort () { StringBuffer sb = new StringBuffer(); for (int i = 0; i < this.size(); i++) { String tt = get(i).toString(); tt.replaceAll("\n",""); if (i > 0){ sb.append(" "); } sb.append(tt); } return sb.toString(); }
public String toStringShort () { StringBuffer sb = new StringBuffer(); for (int i = 0; i < this.size(); i++) { String tt = get(i).toString(); tt.replaceAll("\n",""); if (i > 0){ sb.append(" "); } sb.append(tt); } return sb.toString(); }
public Instance pipe (Instance instance) { TokenSequence sequence = (TokenSequence) instance.getData(); Token token = sequence.get(0); token.setFeatureValue(featureName, 1.0); return instance; }
public Instance pipe (Instance instance) { TokenSequence sequence = (TokenSequence) instance.getData(); Token token = sequence.get(0); token.setFeatureValue(featureName, 1.0); return instance; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); String s = t.getText(); if (s.length() > prefixLength) t.setFeatureValue ((prefix + s.substring (0, prefixLength)), 1.0); } return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); String s = t.getText(); if (s.length() > prefixLength) t.setFeatureValue ((prefix + s.substring (0, prefixLength)), 1.0); } return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); String s = t.getText(); int slen = s.length(); if (slen > suffixLength) t.setFeatureValue ((prefix + s.substring (slen - suffixLength, slen)), 1.0); } return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); String s = t.getText(); if (s.length() > prefixLength) t.setFeatureValue ((prefix + s.substring (0, prefixLength)), 1.0); } return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); t.setText(t.getText().toLowerCase()); } return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); for (int i = 0; i < ts.size(); i++) { Token t = ts.get(i); if (matchingRegex == null || matchingRegex.matcher(t.getText()).matches()) { t.setFeatureValue (prefix == null ? t.getText() : (prefix+t.getText()), 1.0); } } return carrier; }
public Instance next () { if (currentIndex >= currentTokenSequence.size()) { currentInstance = source.next(); currentTokenSequence = (TokenSequence) currentInstance.getData(); } Instance ret = new Instance (currentTokenSequence.get(currentIndex), ((LabelSequence)currentInstance.getTarget()).getLabelAtPosition(currentIndex), null, null); currentIndex++; return ret; } public boolean hasNext () {
public FeatureSequence toFeatureSequence (Alphabet dict) { FeatureSequence fs = new FeatureSequence( dict, this.size() ); for (int i = 0; i < this.size(); i++) fs.add (dict.lookupIndex( (this.get(i)).getText())); return fs; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); FeatureSequence ret = new FeatureSequence ((Alphabet)getDataAlphabet(), ts.size()); for (int i = 0; i < ts.size(); i++) { ret.add (ts.get(i).getText()); } carrier.setData(ret); return carrier; }
public Instance pipe (Instance carrier) { TokenSequence ts = (TokenSequence) carrier.getData(); FeatureSequence ret = new FeatureSequence ((Alphabet)getDataAlphabet(), ts.size()); for (int i = 0; i < ts.size(); i++) { ret.add (ts.get(i).getText()); } carrier.setData(ret); return carrier; }