private static void processFileList(String fileList) throws IOException {
// open list of files
BufferedReader reader = new BufferedReader(new FileReader(fileList));
int docCount = 0;
String currentDoc;
while ((currentDoc = reader.readLine()) != null) {
// process file 'currentDoc'
docCount++;
System.out.println("\nProcessing document " + docCount + ": " + currentDoc);
String textFileName = ACEdir + currentDoc + ".sgm";
ExternalDocument doc = new ExternalDocument("sgml", textFileName);
doc.setAllTags(true);
doc.open();
String APFfileName = ACEdir + currentDoc + apfExtension;
AceDocument aceDoc = new AceDocument(textFileName, APFfileName);
addMentionTags(doc, aceDoc);
doc.setSGMLwrapMargin(0);
doc.saveAs(outputDir, currentDoc + ".co.txt");
}
reader.close();
}
/**
* train the tagger using the DocumentCollection in file 'trainingCollection'.
* 'trainingCollection' should consist of documents which have been explicitly tagged with
* part-of-speech information.
*/
void train(String trainingCollection) {
for (int i = 0; i < posTable.length; i++)
tagTable[i] = new String[] {"constit", "cat", posTable[i], posTable[i]};
// build ergodic HMM with one state for each POS (plus start and end states)
HMMstate startState = new HMMstate("start", "", WordFeatureHMMemitter.class);
posh.addState(startState);
for (int j = 0; j < posTable.length; j++) startState.addArc(new HMMarc(posTable[j], 0));
HMMstate endState = new HMMstate("end", "", WordFeatureHMMemitter.class);
posh.addState(endState);
for (int i = 0; i < posTable.length; i++) {
String pos = posTable[i];
HMMstate state = new HMMstate(pos, pos, WordFeatureHMMemitter.class);
posh.addState(state);
for (int j = 0; j < posTable.length; j++) state.addArc(new HMMarc(posTable[j], 0));
state.addArc(new HMMarc("end", 0));
}
posh.resolveNames();
posh.resetForTraining();
annotator = new HMMannotator(posh);
annotator.setTagTable(tagTable);
annotator.setBItag(false);
DocumentCollection col = new DocumentCollection(trainingCollection);
col.open();
for (int i = 0; i < col.size(); i++) {
ExternalDocument doc = col.get(i);
doc.open();
System.out.println("Training from " + doc.fileName());
// divide at endmarks (constit cat="."), adding "S" marks
int posn = 0;
int start = posn;
Vector anns;
while ((anns = doc.annotationsAt(posn, "constit")) != null) {
Annotation ann = (Annotation) anns.get(0);
posn = ann.span().end();
String pos = (String) ann.get("cat");
if (pos.equals(".")) {
doc.annotate("S", new Span(start, posn), new FeatureSet());
start = posn;
}
}
annotator.train(doc);
// free up space taken by annotations on document
doc.clearAnnotations();
}
posh.computeProbabilities();
}
/** process a single file, 'docName', generating a file with in-line XML. */
public static void processFile(String docName) {
docCount++;
System.out.println("\nProcessing document " + docCount + ": " + docName);
String textFileName = ACEdir + docName + ".sgm";
ExternalDocument doc = new ExternalDocument("sgml", textFileName);
doc.setAllTags(true);
if (year.equals("2003") || year.equals("2004")) doc.setEmptyTags(new String[] {"TURN"});
doc.open();
String APFfileName = ACEdir + docName + "." + apfExtension;
AceDocument aceDoc = new AceDocument(textFileName, APFfileName);
addAnnotations(doc, aceDoc);
doc.setSGMLwrapMargin(0);
doc.saveAs(outputDir, docName + "." + outputExtension);
}