// Output in .rc form
public String toString() {
StringBuilder rc = new StringBuilder();
for (String key : keySet()) {
List<Triple> list = getTriples(key);
for (Triple triple : list) {
String line = triple.toString();
rc.append(line);
rc.append("\n");
}
}
return rc.toString();
}
/**
* Populates the namespaces map with default namespaces and namespaces used by the graph.
*
* @param graph Graph
* @throws GraphException
*/
protected void populateNamespaces(Graph graph) throws GraphException {
// default namespaces
namespaces = new HashMap<String, String>();
namespaces.put(RDF_PREFIX, RDF.BASE_URI.toString());
namespaces.put(RDFS_PREFIX, RDFS.BASE_URI.toString());
namespaces.put("owl", "http://www.w3.org/2002/07/owl#");
namespaces.put("dc", "http://purl.org/dc/elements/1.1/");
// validate graph before reading
if (graph == null) {
throw new IllegalArgumentException("Graph argument is null.");
}
// get all statements
ClosableIterator<Triple> tripleIter = graph.find(null, null, null);
if (tripleIter != null) {
while (tripleIter.hasNext()) {
// get the next triple
Triple triple = tripleIter.next();
if (triple != null) {
// evaluate subject
SubjectNode subject = triple.getSubject();
if (subject instanceof URIReference) {
addNamespaceURI(((URIReference) subject).getURI());
}
// evaluate predicate (must be URIReference)
PredicateNode predicate = triple.getPredicate();
addNamespaceURI(((URIReference) predicate).getURI());
// evaluate object
ObjectNode object = triple.getObject();
if (object instanceof URIReference) {
addNamespaceURI(((URIReference) object).getURI());
}
}
}
// close the Iterator
tripleIter.close();
}
}
private void addColliders(
Graph graph, final SepsetProducer sepsetProducer, IKnowledge knowledge) {
final Map<Triple, Double> collidersPs =
findCollidersUsingSepsets(sepsetProducer, graph, verbose, knowledge);
List<Triple> colliders = new ArrayList<>(collidersPs.keySet());
Collections.shuffle(colliders);
Collections.sort(
colliders,
new Comparator<Triple>() {
public int compare(Triple o1, Triple o2) {
return -Double.compare(collidersPs.get(o1), collidersPs.get(o2));
}
});
if (trueDag != null) {
for (Triple collider : colliders) {
Node a = collider.getX();
Node b = collider.getY();
Node c = collider.getZ();
List<Node> sep = trueDag.getSepset(a, c);
System.out.println(
"JJJ "
+ collider
+ " collider = "
+ (sep != null && !sep.contains(b))
+ " p = "
+ collidersPs.get(collider));
}
}
for (Triple collider : colliders) {
Node a = collider.getX();
Node b = collider.getY();
Node c = collider.getZ();
if (!(isArrowpointAllowed(a, b, knowledge) && isArrowpointAllowed(c, b, knowledge))) {
continue;
}
if (!graph.getEdge(a, b).pointsTowards(a) && !graph.getEdge(b, c).pointsTowards(c)) {
graph.setEndpoint(a, b, Endpoint.ARROW);
graph.setEndpoint(c, b, Endpoint.ARROW);
}
}
}
/**
* The core implementation of the search.
*
* @param root The root word to search from. Traditionally, this is the root of the sentence.
* @param candidateFragments The callback for the resulting sentence fragments. This is a
* predicate of a triple of values. The return value of the predicate determines whether we
* should continue searching. The triple is a triple of
* <ol>
* <li>The log probability of the sentence fragment, according to the featurizer and the
* weights
* <li>The features along the path to this fragment. The last element of this is the
* features from the most recent step.
* <li>The sentence fragment. Because it is relatively expensive to compute the resulting
* tree, this is returned as a lazy {@link Supplier}.
* </ol>
*
* @param classifier The classifier for whether an arc should be on the path to a clause split, a
* clause split itself, or neither.
* @param featurizer The featurizer to use. Make sure this matches the weights!
* @param actionSpace The action space we are allowed to take. Each action defines a means of
* splitting a clause on a dependency boundary.
*/
protected void search(
// The root to search from
IndexedWord root,
// The output specs
final Predicate<Triple<Double, List<Counter<String>>, Supplier<SentenceFragment>>>
candidateFragments,
// The learning specs
final Classifier<ClauseSplitter.ClauseClassifierLabel, String> classifier,
Map<String, ? extends List<String>> hardCodedSplits,
final Function<Triple<State, Action, State>, Counter<String>> featurizer,
final Collection<Action> actionSpace,
final int maxTicks) {
// (the fringe)
PriorityQueue<Pair<State, List<Counter<String>>>> fringe = new FixedPrioritiesPriorityQueue<>();
// (avoid duplicate work)
Set<IndexedWord> seenWords = new HashSet<>();
State firstState =
new State(null, null, -9000, null, x -> {}, true); // First state is implicitly "done"
fringe.add(Pair.makePair(firstState, new ArrayList<>(0)), -0.0);
int ticks = 0;
while (!fringe.isEmpty()) {
if (++ticks > maxTicks) {
// System.err.println("WARNING! Timed out on search with " + ticks + " ticks");
return;
}
// Useful variables
double logProbSoFar = fringe.getPriority();
assert logProbSoFar <= 0.0;
Pair<State, List<Counter<String>>> lastStatePair = fringe.removeFirst();
State lastState = lastStatePair.first;
List<Counter<String>> featuresSoFar = lastStatePair.second;
IndexedWord rootWord = lastState.edge == null ? root : lastState.edge.getDependent();
// Register thunk
if (lastState.isDone) {
if (!candidateFragments.test(
Triple.makeTriple(
logProbSoFar,
featuresSoFar,
() -> {
SemanticGraph copy = new SemanticGraph(tree);
lastState
.thunk
.andThen(
x -> {
// Add the extra edges back in, if they don't break the tree-ness of the
// extraction
for (IndexedWord newTreeRoot : x.getRoots()) {
if (newTreeRoot != null) { // what a strange thing to have happen...
for (SemanticGraphEdge extraEdge :
extraEdgesByGovernor.get(newTreeRoot)) {
assert Util.isTree(x);
//noinspection unchecked
addSubtree(
x,
newTreeRoot,
extraEdge.getRelation().toString(),
tree,
extraEdge.getDependent(),
tree.getIncomingEdgesSorted(newTreeRoot));
assert Util.isTree(x);
}
}
}
})
.accept(copy);
return new SentenceFragment(copy, assumedTruth, false);
}))) {
break;
}
}
// Find relevant auxilliary terms
SemanticGraphEdge subjOrNull = null;
SemanticGraphEdge objOrNull = null;
for (SemanticGraphEdge auxEdge : tree.outgoingEdgeIterable(rootWord)) {
String relString = auxEdge.getRelation().toString();
if (relString.contains("obj")) {
objOrNull = auxEdge;
} else if (relString.contains("subj")) {
subjOrNull = auxEdge;
}
}
// Iterate over children
// For each outgoing edge...
for (SemanticGraphEdge outgoingEdge : tree.outgoingEdgeIterable(rootWord)) {
// Prohibit indirect speech verbs from splitting off clauses
// (e.g., 'said', 'think')
// This fires if the governor is an indirect speech verb, and the outgoing edge is a ccomp
if (outgoingEdge.getRelation().toString().equals("ccomp")
&& ((outgoingEdge.getGovernor().lemma() != null
&& INDIRECT_SPEECH_LEMMAS.contains(outgoingEdge.getGovernor().lemma()))
|| INDIRECT_SPEECH_LEMMAS.contains(outgoingEdge.getGovernor().word()))) {
continue;
}
// Get some variables
String outgoingEdgeRelation = outgoingEdge.getRelation().toString();
List<String> forcedArcOrder = hardCodedSplits.get(outgoingEdgeRelation);
if (forcedArcOrder == null && outgoingEdgeRelation.contains(":")) {
forcedArcOrder =
hardCodedSplits.get(
outgoingEdgeRelation.substring(0, outgoingEdgeRelation.indexOf(":")) + ":*");
}
boolean doneForcedArc = false;
// For each action...
for (Action action :
(forcedArcOrder == null ? actionSpace : orderActions(actionSpace, forcedArcOrder))) {
// Check the prerequisite
if (!action.prerequisitesMet(tree, outgoingEdge)) {
continue;
}
if (forcedArcOrder != null && doneForcedArc) {
break;
}
// 1. Compute the child state
Optional<State> candidate =
action.applyTo(tree, lastState, outgoingEdge, subjOrNull, objOrNull);
if (candidate.isPresent()) {
double logProbability;
ClauseClassifierLabel bestLabel;
Counter<String> features =
featurizer.apply(Triple.makeTriple(lastState, action, candidate.get()));
if (forcedArcOrder != null && !doneForcedArc) {
logProbability = 0.0;
bestLabel = ClauseClassifierLabel.CLAUSE_SPLIT;
doneForcedArc = true;
} else if (features.containsKey("__undocumented_junit_no_classifier")) {
logProbability = Double.NEGATIVE_INFINITY;
bestLabel = ClauseClassifierLabel.CLAUSE_INTERM;
} else {
Counter<ClauseClassifierLabel> scores = classifier.scoresOf(new RVFDatum<>(features));
if (scores.size() > 0) {
Counters.logNormalizeInPlace(scores);
}
String rel = outgoingEdge.getRelation().toString();
if ("nsubj".equals(rel) || "dobj".equals(rel)) {
scores.remove(
ClauseClassifierLabel.NOT_A_CLAUSE); // Always at least yield on nsubj and dobj
}
logProbability = Counters.max(scores, Double.NEGATIVE_INFINITY);
bestLabel = Counters.argmax(scores, (x, y) -> 0, ClauseClassifierLabel.CLAUSE_SPLIT);
}
if (bestLabel != ClauseClassifierLabel.NOT_A_CLAUSE) {
Pair<State, List<Counter<String>>> childState =
Pair.makePair(
candidate.get().withIsDone(bestLabel),
new ArrayList<Counter<String>>(featuresSoFar) {
{
add(features);
}
});
// 2. Register the child state
if (!seenWords.contains(childState.first.edge.getDependent())) {
// System.err.println(" pushing " + action.signature() + " with " +
// argmax.first.edge);
fringe.add(childState, logProbability);
}
}
}
}
}
seenWords.add(rootWord);
}
// System.err.println("Search finished in " + ticks + " ticks and " + classifierEvals + "
// classifier evaluations.");
}