private InstanceList prepareInstanceList(String[] sections) {
InstanceList instanceList = new InstanceList(pipe);
// prepare training data
for (String section : sections) {
File pdtbSection = new File(pdtbRoot, section);
File[] pdtbFiles = pdtbSection.listFiles(new FileExtensionFilter(".pipe"));
for (File pdtbFile : pdtbFiles) {
File ptbFile =
new File(ptbRoot, section + "/" + pdtbFile.getName().replace(".pipe", ".mrg"));
File depFile =
new File(depRoot, section + "/" + pdtbFile.getName().replace(".pipe", ".dep"));
List<PDTBRelation> relations = pipedFileReader.read(pdtbFile);
Document document = new Document(ptbFile, depFile);
for (PDTBRelation relation : relations) {
if (relation.getType().equals("Explicit")) {
String gornAddress1 = relation.getArg1GornAddress();
if (gornAddress1.equals("") || gornAddress1.contains(";;")) {
continue;
}
GornAddressList gaList1 = new GornAddressList(gornAddress1);
int lineNumber1 = gaList1.get(0).getLineNumber();
String connGornAddress = relation.getConnectiveGornAddress();
if (connGornAddress.equals("")) continue;
GornAddressList connGAList = new GornAddressList(connGornAddress);
String gornAddress2 = relation.getArg2GornAddress();
if (gornAddress2.equals("") || gornAddress2.contains(";;")) {
continue;
}
int lineNumber2 = connGAList.get(0).getLineNumber();
addInstancesThroughPipe(relation, document, lineNumber1, lineNumber2, instanceList);
}
}
}
}
return instanceList;
}
private void addInstancesThroughPipe(
PDTBRelation relation,
Document document,
int arg1Line,
int arg2Line,
InstanceList instanceList) {
// System.out.println("Relation: " + relation.toString());
// System.out.println("arg1Line: " + arg1Line);
// System.out.println("arg2Line: " + arg2Line);
String connectiveGornAddress = relation.getConnectiveGornAddress();
Tree arg2Tree = document.getTree(arg2Line);
List<Tree> connHeadLeaves =
connAnalyzer.getConnHeadLeaves(arg2Tree, connectiveGornAddress, relation.getConnHead());
if (connHeadLeaves.isEmpty()) return;
int connStart = treeAnalyzer.getLeafPosition(arg2Tree, connHeadLeaves.get(0));
int connEnd =
treeAnalyzer.getLeafPosition(arg2Tree, connHeadLeaves.get(connHeadLeaves.size() - 1));
if ((connEnd - connStart) > 4) { // handle if..else, etc.
connEnd = connStart;
}
// consider only the first sentence in case of multi-line argument1
String arg1GornAddress = relation.getArg1GornAddress();
Tree arg1Tree = document.getTree(arg1Line);
List<Tree> arg1GornNodes = getArgGornNodes(arg1Tree, arg1Line, arg1GornAddress);
Tree syntacticHead = headAnalyzer.getSyntacticHead(arg1Tree, arg1GornNodes);
int arg1HeadPos = treeAnalyzer.getLeafPosition(arg1Tree, syntacticHead);
String arg2GornAddress = relation.getArg2GornAddress();
List<Tree> arg2GornNodes = getArgGornNodes(arg2Tree, arg2Line, arg2GornAddress);
Tree arg2SyntacticHead = headAnalyzer.getSyntacticHead(arg2Tree, arg2GornNodes);
int arg2HeadPos = treeAnalyzer.getLeafPosition(arg2Tree, arg2SyntacticHead);
if (arg2HeadPos == -1) {
System.out.println("arg2Head == -1");
return;
}
if (arg1HeadPos == -1) {
System.out.println("arg1Head == -1");
return;
}
int trueCandidate = -1;
List<Pair<Integer, Integer>> candidates =
getCandidates(document, arg2Line, connStart, connEnd, arg1Line);
for (int i = 0; i < candidates.size(); i++) {
Pair<Integer, Integer> candidate = candidates.get(i);
if (candidate.first() == arg1Line && candidate.second() == arg1HeadPos) {
trueCandidate = i;
break;
}
}
if (trueCandidate == -1) {
// trueCandidate = candidates.size();
// candidates.add(new Pair<Integer, Integer>(arg1Line, arg1HeadPos));
// System.out.println("Covered!");
System.out.println("true candidate == -1!!!");
System.out.println(syntacticHead.value());
} else {
int extractArg2 =
ARG2_EXTRACTOR.extractArg2(
document.getSentence(arg2Line),
document.getTree(arg2Line),
document.getDepGraph(arg2Line),
connStart,
connEnd);
if (extractArg2 == -1) {
extractArg2 = 0;
System.out.println("Arg2 == -1!!!!!!!!!!!!!!!!!");
}
// Arg1RankInstance instance = new Arg1RankInstance(document, candidates, arg2Line,
// extractArg2, connStart, connEnd, trueCandidate);
Arg1RankInstance instance =
new Arg1RankInstance(
document, candidates, arg2Line, arg2HeadPos, connStart, connEnd, trueCandidate);
instanceList.addThruPipe(instance);
}
}