/**
* TODO(gabor) JavaDoc
*
* @param tokens
* @param span
* @return
*/
public static String guessNER(List<CoreLabel> tokens, Span span) {
Counter<String> nerGuesses = new ClassicCounter<>();
for (int i : span) {
nerGuesses.incrementCount(tokens.get(i).ner());
}
nerGuesses.remove("O");
nerGuesses.remove(null);
if (nerGuesses.size() > 0 && Counters.max(nerGuesses) >= span.size() / 2) {
return Counters.argmax(nerGuesses);
} else {
return "O";
}
}
@Deprecated
protected void semanticSimilarity(
Counter<String> features, String prefix, Sentence str1, Sentence str2) {
Counter<String> v1 =
new ClassicCounter<>(
str1.lemmas().stream().map(String::toLowerCase).collect(Collectors.toList()));
Counter<String> v2 = new ClassicCounter<>(str2.lemmas());
// Remove any stopwords.
for (String word : stopwords) {
v1.remove(word);
v2.remove(word);
}
// take inner product.
double sim =
Counters.dotProduct(v1, v2) / (Counters.saferL2Norm(v1) * Counters.saferL2Norm(v2));
features.incrementCount(
prefix + "semantic-similarity", 2 * sim - 1); // to make it between 0 and 1.
}
/**
* This should be called after the classifier has been trained and parseAndTrain has been called
* to accumulate test set
*
* <p>This will return precision,recall and F1 measure
*/
public void runTestSet(List<List<CoreLabel>> testSet) {
Counter<String> tp = new DefaultCounter<>();
Counter<String> fp = new DefaultCounter<>();
Counter<String> fn = new DefaultCounter<>();
Counter<String> actual = new DefaultCounter<>();
for (List<CoreLabel> labels : testSet) {
List<CoreLabel> unannotatedLabels = new ArrayList<>();
// create a new label without answer annotation
for (CoreLabel label : labels) {
CoreLabel newLabel = new CoreLabel();
newLabel.set(annotationForWord, label.get(annotationForWord));
newLabel.set(PartOfSpeechAnnotation.class, label.get(PartOfSpeechAnnotation.class));
unannotatedLabels.add(newLabel);
}
List<CoreLabel> annotatedLabels = this.classifier.classify(unannotatedLabels);
int ind = 0;
for (CoreLabel expectedLabel : labels) {
CoreLabel annotatedLabel = annotatedLabels.get(ind);
String answer = annotatedLabel.get(AnswerAnnotation.class);
String expectedAnswer = expectedLabel.get(AnswerAnnotation.class);
actual.incrementCount(expectedAnswer);
// match only non background symbols
if (!SeqClassifierFlags.DEFAULT_BACKGROUND_SYMBOL.equals(expectedAnswer)
&& expectedAnswer.equals(answer)) {
// true positives
tp.incrementCount(answer);
System.out.println("True Positive:" + annotatedLabel);
} else if (!SeqClassifierFlags.DEFAULT_BACKGROUND_SYMBOL.equals(answer)) {
// false positives
fp.incrementCount(answer);
System.out.println("False Positive:" + annotatedLabel);
} else if (!SeqClassifierFlags.DEFAULT_BACKGROUND_SYMBOL.equals(expectedAnswer)) {
// false negatives
fn.incrementCount(expectedAnswer);
System.out.println("False Negative:" + expectedLabel);
} // else true negatives
ind++;
}
}
actual.remove(SeqClassifierFlags.DEFAULT_BACKGROUND_SYMBOL);
}
/**
* 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.");
}