@Override
public Set<Feature> getFeatures(Constituent c) throws EdisonException {
TextAnnotation ta = c.getTextAnnotation();
Set<Feature> features = new LinkedHashSet<>();
TreeView parse = (TreeView) ta.getView(dependencyViewName);
// get equivalent of c in the parse view
Constituent c2 = parse.getConstituentsCoveringToken(c.getStartSpan()).get(0);
List<Relation> incomingRelations = c2.getIncomingRelations();
if (incomingRelations.size() > 0) {
Constituent c1 =
parse
.getConstituentsCoveringToken(incomingRelations.get(0).getSource().getStartSpan())
.get(0);
Pair<List<Constituent>, List<Constituent>> paths =
PathFeatureHelper.getPathsToCommonAncestor(c1, c2, 400);
List<String> path = new ArrayList<>();
List<String> pos = new ArrayList<>();
for (int i = 0; i < paths.getFirst().size() - 1; i++) {
Constituent cc = paths.getFirst().get(i);
path.add(
cc.getIncomingRelations().get(0).getRelationName() + PathFeatureHelper.PATH_UP_STRING);
pos.add(
WordHelpers.getPOS(ta, cc.getStartSpan())
+ ":"
+ cc.getIncomingRelations().get(0).getRelationName()
+ PathFeatureHelper.PATH_UP_STRING);
}
Constituent top = paths.getFirst().get(paths.getFirst().size() - 1);
pos.add(WordHelpers.getPOS(ta, top.getStartSpan()) + ":*");
path.add("*");
if (paths.getSecond().size() > 1) {
for (int i = paths.getSecond().size() - 2; i >= 0; i--) {
Constituent cc = paths.getSecond().get(i);
pos.add(
WordHelpers.getPOS(ta, cc.getStartSpan()) + ":" + PathFeatureHelper.PATH_DOWN_STRING);
path.add(PathFeatureHelper.PATH_DOWN_STRING);
}
}
features.addAll(getNgrams(path, ""));
features.addAll(getNgrams(pos, "pos"));
}
return features;
}
private static Constituent getHead(Constituent c, TreeView dependency) {
Constituent end = null;
List<Constituent> constituentsCovering = dependency.getConstituentsCovering(c);
for (Constituent d : constituentsCovering) {
List<Relation> in = d.getIncomingRelations();
if (in.size() == 0) {
end = d;
break;
} else {
Constituent parent = in.get(0).getSource();
int parentToken = parent.getStartSpan();
if (c.getStartSpan() <= parentToken && parentToken < c.getEndSpan()) continue;
if (end == null) {
end = d;
} else if (end.getStartSpan() < d.getStartSpan()) {
end = d;
}
}
}
Constituent c1;
if (end == null) c1 = constituentsCovering.get(0).cloneForNewView("");
else c1 = end.cloneForNewView("");
return addPointerToSource(c, c1);
}
@Override
public List<Constituent> transform(Constituent input) {
TextAnnotation ta = input.getTextAnnotation();
int tokenPosition = input.getStartSpan();
TreeView dependency = (TreeView) ta.getView(ViewNames.DEPENDENCY);
Constituent verbNode = dependency.getConstituentsCoveringToken(tokenPosition).get(0);
boolean done = false;
while (!done) {
String pos = WordHelpers.getPOS(ta, verbNode.getStartSpan());
if (POSUtils.isPOSVerb(pos)) {
done = true;
} else {
List<Relation> incoming = verbNode.getIncomingRelations();
if (incoming == null || incoming.size() == 0) {
return new ArrayList<>();
} else verbNode = incoming.get(0).getSource();
}
}
return Collections.singletonList(addPointerToSource(input, verbNode));
}
@Override
public List<Constituent> transform(Constituent input) {
List<Constituent> c = new ArrayList<>();
for (Relation r : input.getIncomingRelations()) {
c.add(addPointerToSource(input, r.getSource()));
}
return c;
}
public Constituent getDependentVerb(Problem prob, QuantSpan qs) {
Constituent result =
getDependencyConstituentCoveringTokenId(
prob, prob.ta.getTokenIdFromCharacterOffset(qs.start));
if (result == null) {
System.out.println(
"Text : "
+ prob.question
+ " Token : "
+ prob.ta.getTokenIdFromCharacterOffset(qs.start));
Tools.printCons(prob.dependency);
}
while (result != null) {
if (result.getIncomingRelations().size() == 0) break;
// System.out.println(result.getIncomingRelations().get(0).getSource()+" --> "+result);
result = result.getIncomingRelations().get(0).getSource();
if (prob.posTags.get(result.getStartSpan()).getLabel().startsWith("VB")) {
return result;
}
}
return result;
}
private static List<Constituent> getGovernor(Constituent input, TreeView dependency) {
List<Constituent> constituentsCovering = dependency.getConstituentsCovering(input);
if (constituentsCovering.size() == 0) return new ArrayList<>();
Constituent c = constituentsCovering.get(0);
List<Relation> incomingRelations = c.getIncomingRelations();
if (incomingRelations == null || incomingRelations.size() == 0) return new ArrayList<>();
else
return Collections.singletonList(
addPointerToSource(input, incomingRelations.get(0).getSource()));
}
@Override
public List<Constituent> transform(Constituent c) {
TextAnnotation ta = c.getTextAnnotation();
int tokenPosition = c.getStartSpan();
TreeView dependency = (TreeView) ta.getView(ViewNames.DEPENDENCY);
Constituent prepositionDepConstituent =
dependency.getConstituentsCoveringToken(tokenPosition).get(0);
List<Relation> incomingRelations = prepositionDepConstituent.getIncomingRelations();
List<Constituent> list = new ArrayList<>();
if (incomingRelations != null && incomingRelations.size() > 0) {
Constituent parent = incomingRelations.get(0).getSource();
for (Relation out : parent.getOutgoingRelations()) {
if (out == incomingRelations.get(0)) continue;
String label = out.getRelationName();
if (label.contains("prep")) {
Constituent ppNode = out.getTarget();
list.add(addPointerToSource(c, ppNode));
// get the first child of the pp and add this
List<Relation> ppOut = ppNode.getOutgoingRelations();
if (ppOut != null && ppOut.size() != 0) {
Constituent child = ppOut.get(0).getTarget();
list.add(addPointerToSource(c, child));
}
}
}
}
return list;
}
