Examples with PosTaggerFeature com.joliciel.talismane.posTagger.features.PosTaggerFeature used on opensource projects

Example 1 with PosTaggerFeature

use of com.joliciel.talismane.posTagger.features.PosTaggerFeature in project talismane by joliciel-informatique.

the class ForwardStatisticalPosTagger method tagSentence.

@Override
public List<PosTagSequence> tagSentence(List<TokenSequence> input) throws TalismaneException, IOException {
    List<TokenSequence> tokenSequences = null;
    if (this.propagateTokeniserBeam) {
        tokenSequences = input;
    } else {
        tokenSequences = new ArrayList<>(1);
        tokenSequences.add(input.get(0));
    }
    int sentenceLength = tokenSequences.get(0).getSentence().getText().length();
    TreeMap<Double, PriorityQueue<PosTagSequence>> heaps = new TreeMap<Double, PriorityQueue<PosTagSequence>>();
    PriorityQueue<PosTagSequence> heap0 = new PriorityQueue<PosTagSequence>();
    for (TokenSequence tokenSequence : tokenSequences) {
        // add an empty PosTagSequence for each token sequence
        PosTagSequence emptySequence = new PosTagSequence(tokenSequence);
        emptySequence.setScoringStrategy(decisionMaker.getDefaultScoringStrategy());
        heap0.add(emptySequence);
    }
    heaps.put(0.0, heap0);
    PriorityQueue<PosTagSequence> finalHeap = null;
    while (heaps.size() > 0) {
        Entry<Double, PriorityQueue<PosTagSequence>> heapEntry = heaps.pollFirstEntry();
        if (LOG.isTraceEnabled()) {
            LOG.trace("heap key: " + heapEntry.getKey() + ", sentence length: " + sentenceLength);
        }
        if (heapEntry.getKey() == sentenceLength) {
            finalHeap = heapEntry.getValue();
            break;
        }
        PriorityQueue<PosTagSequence> previousHeap = heapEntry.getValue();
        // limit the breadth to K
        int maxSequences = previousHeap.size() > this.beamWidth ? this.beamWidth : previousHeap.size();
        for (int j = 0; j < maxSequences; j++) {
            PosTagSequence history = previousHeap.poll();
            Token token = history.getNextToken();
            if (LOG.isTraceEnabled()) {
                LOG.trace("#### Next history ( " + heapEntry.getKey() + "): " + history.toString());
                LOG.trace("Prob: " + df.format(history.getScore()));
                LOG.trace("Token: " + token.getText());
                StringBuilder sb = new StringBuilder();
                for (Token oneToken : history.getTokenSequence().listWithWhiteSpace()) {
                    if (oneToken.equals(token))
                        sb.append("[" + oneToken + "]");
                    else
                        sb.append(oneToken);
                }
                LOG.trace(sb.toString());
            }
            PosTaggerContext context = new PosTaggerContextImpl(token, history);
            List<Decision> decisions = new ArrayList<Decision>();
            boolean ruleApplied = false;
            // assigned?
            if (token.getAttributes().containsKey(PosTagger.POS_TAG_ATTRIBUTE)) {
                StringAttribute posTagCodeAttribute = (StringAttribute) token.getAttributes().get(PosTagger.POS_TAG_ATTRIBUTE);
                String posTagCode = posTagCodeAttribute.getValue();
                Decision positiveRuleDecision = new Decision(posTagCode);
                decisions.add(positiveRuleDecision);
                positiveRuleDecision.addAuthority("tokenAttribute");
                ruleApplied = true;
                if (LOG.isTraceEnabled()) {
                    LOG.trace("Token has attribute \"" + PosTagger.POS_TAG_ATTRIBUTE + "\". Setting posTag to: " + posTagCode);
                }
            }
            // test the positive rules on the current token
            if (!ruleApplied) {
                if (posTaggerPositiveRules != null) {
                    for (PosTaggerRule rule : posTaggerPositiveRules) {
                        if (LOG.isTraceEnabled()) {
                            LOG.trace("Checking rule: " + rule.getCondition().getName());
                        }
                        RuntimeEnvironment env = new RuntimeEnvironment();
                        FeatureResult<Boolean> ruleResult = rule.getCondition().check(context, env);
                        if (ruleResult != null && ruleResult.getOutcome()) {
                            Decision positiveRuleDecision = new Decision(rule.getTag().getCode());
                            decisions.add(positiveRuleDecision);
                            positiveRuleDecision.addAuthority(rule.getCondition().getName());
                            ruleApplied = true;
                            if (LOG.isTraceEnabled()) {
                                LOG.trace("Rule applies. Setting posTag to: " + rule.getTag().getCode());
                            }
                            break;
                        }
                    }
                }
            }
            if (!ruleApplied) {
                // test the features on the current token
                List<FeatureResult<?>> featureResults = new ArrayList<FeatureResult<?>>();
                for (PosTaggerFeature<?> posTaggerFeature : posTaggerFeatures) {
                    RuntimeEnvironment env = new RuntimeEnvironment();
                    FeatureResult<?> featureResult = posTaggerFeature.check(context, env);
                    if (featureResult != null)
                        featureResults.add(featureResult);
                }
                if (LOG.isTraceEnabled()) {
                    SortedSet<String> featureResultSet = featureResults.stream().map(f -> f.toString()).collect(Collectors.toCollection(() -> new TreeSet<String>()));
                    for (String featureResultString : featureResultSet) {
                        LOG.trace(featureResultString);
                    }
                }
                // evaluate the feature results using the maxent model
                decisions = this.decisionMaker.decide(featureResults);
                for (ClassificationObserver observer : this.observers) {
                    observer.onAnalyse(token, featureResults, decisions);
                }
                // apply the negative rules
                Set<String> eliminatedPosTags = new TreeSet<String>();
                if (posTaggerNegativeRules != null) {
                    for (PosTaggerRule rule : posTaggerNegativeRules) {
                        if (LOG.isTraceEnabled()) {
                            LOG.trace("Checking negative rule: " + rule.getCondition().getName());
                        }
                        RuntimeEnvironment env = new RuntimeEnvironment();
                        FeatureResult<Boolean> ruleResult = rule.getCondition().check(context, env);
                        if (ruleResult != null && ruleResult.getOutcome()) {
                            eliminatedPosTags.add(rule.getTag().getCode());
                            if (LOG.isTraceEnabled()) {
                                LOG.trace("Rule applies. Eliminating posTag: " + rule.getTag().getCode());
                            }
                        }
                    }
                    if (eliminatedPosTags.size() > 0) {
                        List<Decision> decisionShortList = new ArrayList<Decision>();
                        for (Decision decision : decisions) {
                            if (!eliminatedPosTags.contains(decision.getOutcome())) {
                                decisionShortList.add(decision);
                            } else {
                                LOG.trace("Eliminating decision: " + decision.toString());
                            }
                        }
                        if (decisionShortList.size() > 0) {
                            decisions = decisionShortList;
                        } else {
                            LOG.debug("All decisions eliminated! Restoring original decisions.");
                        }
                    }
                }
                // is this a known word in the lexicon?
                if (LOG.isTraceEnabled()) {
                    String posTags = "";
                    for (PosTag onePosTag : token.getPossiblePosTags()) {
                        posTags += onePosTag.getCode() + ",";
                    }
                    LOG.trace("Token: " + token.getText() + ". PosTags: " + posTags);
                }
                List<Decision> decisionShortList = new ArrayList<Decision>();
                for (Decision decision : decisions) {
                    if (decision.getProbability() >= MIN_PROB_TO_STORE) {
                        decisionShortList.add(decision);
                    }
                }
                if (decisionShortList.size() > 0) {
                    decisions = decisionShortList;
                }
            }
            // outcome provided by MaxEnt
            for (Decision decision : decisions) {
                if (LOG.isTraceEnabled())
                    LOG.trace("Outcome: " + decision.getOutcome() + ", " + decision.getProbability());
                PosTaggedToken posTaggedToken = new PosTaggedToken(token, decision, this.sessionId);
                PosTagSequence sequence = new PosTagSequence(history);
                sequence.addPosTaggedToken(posTaggedToken);
                if (decision.isStatistical())
                    sequence.addDecision(decision);
                double heapIndex = token.getEndIndex();
                // it from regular ones
                if (token.getStartIndex() == token.getEndIndex())
                    heapIndex += 0.5;
                // if it's the last token, make sure we end
                if (token.getIndex() == sequence.getTokenSequence().size() - 1)
                    heapIndex = sentenceLength;
                if (LOG.isTraceEnabled())
                    LOG.trace("Heap index: " + heapIndex);
                PriorityQueue<PosTagSequence> heap = heaps.get(heapIndex);
                if (heap == null) {
                    heap = new PriorityQueue<PosTagSequence>();
                    heaps.put(heapIndex, heap);
                }
                heap.add(sequence);
            }
        // next outcome for this token
        }
    // next history
    }
    // next atomic index
    // return the best sequence on the heap
    List<PosTagSequence> sequences = new ArrayList<PosTagSequence>();
    int i = 0;
    while (!finalHeap.isEmpty()) {
        // clone the pos tag sequences to ensure they don't share any underlying
        // data (e.g. token sequences)
        sequences.add(finalHeap.poll().clonePosTagSequence());
        i++;
        if (i >= this.getBeamWidth())
            break;
    }
    // apply post-processing filters
    if (LOG.isDebugEnabled()) {
        LOG.debug("####Final postag sequences:");
        int j = 1;
        for (PosTagSequence sequence : sequences) {
            if (LOG.isDebugEnabled()) {
                LOG.debug("Sequence " + (j++) + ", score=" + df.format(sequence.getScore()));
                LOG.debug("Sequence: " + sequence);
            }
        }
    }
    return sequences;
}

Example 2 with PosTaggerFeature

use of com.joliciel.talismane.posTagger.features.PosTaggerFeature in project talismane by joliciel-informatique.

the class PosTagEventStream method next.

@Override
public ClassificationEvent next() throws TalismaneException, IOException {
    ClassificationEvent event = null;
    if (this.hasNext()) {
        PosTaggedToken taggedToken = currentSentence.get(currentIndex++);
        String classification = taggedToken.getTag().getCode();
        if (LOG.isDebugEnabled())
            LOG.debug("next event, token: " + taggedToken.getToken().getAnalyisText() + " : " + classification);
        PosTaggerContext context = new PosTaggerContextImpl(taggedToken.getToken(), currentHistory);
        List<FeatureResult<?>> posTagFeatureResults = new ArrayList<FeatureResult<?>>();
        for (PosTaggerFeature<?> posTaggerFeature : posTaggerFeatures) {
            RuntimeEnvironment env = new RuntimeEnvironment();
            FeatureResult<?> featureResult = posTaggerFeature.check(context, env);
            if (featureResult != null)
                posTagFeatureResults.add(featureResult);
        }
        if (LOG.isTraceEnabled()) {
            LOG.trace("Token: " + taggedToken.getToken().getAnalyisText());
            SortedSet<String> featureResultSet = posTagFeatureResults.stream().map(f -> f.toString()).collect(Collectors.toCollection(() -> new TreeSet<String>()));
            for (String featureResultString : featureResultSet) {
                LOG.trace(featureResultString);
            }
        }
        event = new ClassificationEvent(posTagFeatureResults, classification);
        currentHistory.addPosTaggedToken(taggedToken);
        if (currentIndex == currentSentence.size()) {
            currentSentence = null;
        }
    }
    return event;
}