@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;
}
@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));
}