Examples with PosTagSequence com.joliciel.talismane.posTagger.PosTagSequence used on opensource projects

Example 1 with PosTagSequence

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

the class TransitionBasedParser method parseSentence.

@Override
public List<ParseConfiguration> parseSentence(List<PosTagSequence> input) throws TalismaneException, IOException {
    List<PosTagSequence> posTagSequences = null;
    if (this.propagatePosTaggerBeam) {
        posTagSequences = input;
    } else {
        posTagSequences = new ArrayList<>(1);
        posTagSequences.add(input.get(0));
    }
    long startTime = System.currentTimeMillis();
    int maxAnalysisTimeMilliseconds = maxAnalysisTimePerSentence * 1000;
    int minFreeMemoryBytes = minFreeMemory * KILOBYTE;
    TokenSequence tokenSequence = posTagSequences.get(0).getTokenSequence();
    TreeMap<Integer, PriorityQueue<ParseConfiguration>> heaps = new TreeMap<>();
    PriorityQueue<ParseConfiguration> heap0 = new PriorityQueue<>();
    for (PosTagSequence posTagSequence : posTagSequences) {
        // add an initial ParseConfiguration for each postag sequence
        ParseConfiguration initialConfiguration = new ParseConfiguration(posTagSequence);
        initialConfiguration.setScoringStrategy(decisionMaker.getDefaultScoringStrategy());
        heap0.add(initialConfiguration);
        if (LOG.isDebugEnabled()) {
            LOG.debug("Adding initial posTagSequence: " + posTagSequence);
        }
    }
    heaps.put(0, heap0);
    PriorityQueue<ParseConfiguration> backupHeap = null;
    PriorityQueue<ParseConfiguration> finalHeap = null;
    PriorityQueue<ParseConfiguration> terminalHeap = new PriorityQueue<>();
    while (heaps.size() > 0) {
        Entry<Integer, PriorityQueue<ParseConfiguration>> heapEntry = heaps.pollFirstEntry();
        PriorityQueue<ParseConfiguration> currentHeap = heapEntry.getValue();
        int currentHeapIndex = heapEntry.getKey();
        if (LOG.isTraceEnabled()) {
            LOG.trace("##### Polling next heap: " + heapEntry.getKey() + ", size: " + heapEntry.getValue().size());
        }
        boolean finished = false;
        // systematically set the final heap here, just in case we exit
        // "naturally" with no more heaps
        finalHeap = heapEntry.getValue();
        backupHeap = new PriorityQueue<>();
        // we jump out when either (a) all tokens have been attached or
        // (b) we go over the max alloted time
        ParseConfiguration topConf = currentHeap.peek();
        if (topConf.isTerminal()) {
            LOG.trace("Exiting with terminal heap: " + heapEntry.getKey() + ", size: " + heapEntry.getValue().size());
            finished = true;
        }
        if (earlyStop && terminalHeap.size() >= beamWidth) {
            LOG.debug("Early stop activated and terminal heap contains " + beamWidth + " entries. Exiting.");
            finalHeap = terminalHeap;
            finished = true;
        }
        long analysisTime = System.currentTimeMillis() - startTime;
        if (maxAnalysisTimePerSentence > 0 && analysisTime > maxAnalysisTimeMilliseconds) {
            LOG.info("Parse tree analysis took too long for sentence: " + tokenSequence.getSentence().getText());
            LOG.info("Breaking out after " + maxAnalysisTimePerSentence + " seconds.");
            finished = true;
        }
        if (minFreeMemory > 0) {
            long freeMemory = Runtime.getRuntime().freeMemory();
            if (freeMemory < minFreeMemoryBytes) {
                LOG.info("Not enough memory left to parse sentence: " + tokenSequence.getSentence().getText());
                LOG.info("Min free memory (bytes):" + minFreeMemoryBytes);
                LOG.info("Current free memory (bytes): " + freeMemory);
                finished = true;
            }
        }
        if (finished) {
            break;
        }
        // limit the breadth to K
        int maxSequences = currentHeap.size() > this.beamWidth ? this.beamWidth : currentHeap.size();
        int j = 0;
        while (currentHeap.size() > 0) {
            ParseConfiguration history = currentHeap.poll();
            if (LOG.isTraceEnabled()) {
                LOG.trace("### Next configuration on heap " + heapEntry.getKey() + ":");
                LOG.trace(history.toString());
                LOG.trace("Score: " + df.format(history.getScore()));
                LOG.trace(history.getPosTagSequence().toString());
            }
            List<Decision> decisions = new ArrayList<>();
            // test the positive rules on the current configuration
            boolean ruleApplied = false;
            if (parserPositiveRules != null) {
                for (ParserRule rule : parserPositiveRules) {
                    if (LOG.isTraceEnabled()) {
                        LOG.trace("Checking rule: " + rule.toString());
                    }
                    RuntimeEnvironment env = new RuntimeEnvironment();
                    FeatureResult<Boolean> ruleResult = rule.getCondition().check(history, env);
                    if (ruleResult != null && ruleResult.getOutcome()) {
                        Decision positiveRuleDecision = new Decision(rule.getTransition().getCode());
                        decisions.add(positiveRuleDecision);
                        positiveRuleDecision.addAuthority(rule.getCondition().getName());
                        ruleApplied = true;
                        if (LOG.isTraceEnabled()) {
                            LOG.trace("Rule applies. Setting transition to: " + rule.getTransition().getCode());
                        }
                        break;
                    }
                }
            }
            if (!ruleApplied) {
                // test the features on the current configuration
                List<FeatureResult<?>> parseFeatureResults = new ArrayList<>();
                for (ParseConfigurationFeature<?> feature : this.parseFeatures) {
                    RuntimeEnvironment env = new RuntimeEnvironment();
                    FeatureResult<?> featureResult = feature.check(history, env);
                    if (featureResult != null)
                        parseFeatureResults.add(featureResult);
                }
                if (LOG_FEATURES.isTraceEnabled()) {
                    SortedSet<String> featureResultSet = parseFeatureResults.stream().map(f -> f.toString()).collect(Collectors.toCollection(() -> new TreeSet<>()));
                    for (String featureResultString : featureResultSet) {
                        LOG_FEATURES.trace(featureResultString);
                    }
                }
                // evaluate the feature results using the decision maker
                decisions = this.decisionMaker.decide(parseFeatureResults);
                for (ClassificationObserver observer : this.observers) {
                    observer.onAnalyse(history, parseFeatureResults, decisions);
                }
                List<Decision> decisionShortList = new ArrayList<>(decisions.size());
                for (Decision decision : decisions) {
                    if (decision.getProbability() > MIN_PROB_TO_STORE)
                        decisionShortList.add(decision);
                }
                decisions = decisionShortList;
                // apply the negative rules
                Set<String> eliminatedTransitions = new HashSet<>();
                if (parserNegativeRules != null) {
                    for (ParserRule rule : parserNegativeRules) {
                        if (LOG.isTraceEnabled()) {
                            LOG.trace("Checking negative rule: " + rule.toString());
                        }
                        RuntimeEnvironment env = new RuntimeEnvironment();
                        FeatureResult<Boolean> ruleResult = rule.getCondition().check(history, env);
                        if (ruleResult != null && ruleResult.getOutcome()) {
                            for (Transition transition : rule.getTransitions()) {
                                eliminatedTransitions.add(transition.getCode());
                                if (LOG.isTraceEnabled())
                                    LOG.trace("Rule applies. Eliminating transition: " + transition.getCode());
                            }
                        }
                    }
                    if (eliminatedTransitions.size() > 0) {
                        decisionShortList = new ArrayList<>();
                        for (Decision decision : decisions) {
                            if (!eliminatedTransitions.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.");
                        }
                    }
                }
            }
            // has a positive rule been applied?
            boolean transitionApplied = false;
            TransitionSystem transitionSystem = TalismaneSession.get(sessionId).getTransitionSystem();
            // type, we should be able to stop
            for (Decision decision : decisions) {
                Transition transition = transitionSystem.getTransitionForCode(decision.getOutcome());
                if (LOG.isTraceEnabled())
                    LOG.trace("Outcome: " + transition.getCode() + ", " + decision.getProbability());
                if (transition.checkPreconditions(history)) {
                    transitionApplied = true;
                    ParseConfiguration configuration = new ParseConfiguration(history);
                    if (decision.isStatistical())
                        configuration.addDecision(decision);
                    transition.apply(configuration);
                    int nextHeapIndex = parseComparisonStrategy.getComparisonIndex(configuration) * 1000;
                    if (configuration.isTerminal()) {
                        nextHeapIndex = Integer.MAX_VALUE;
                    } else {
                        while (nextHeapIndex <= currentHeapIndex) nextHeapIndex++;
                    }
                    PriorityQueue<ParseConfiguration> nextHeap = heaps.get(nextHeapIndex);
                    if (nextHeap == null) {
                        if (configuration.isTerminal())
                            nextHeap = terminalHeap;
                        else
                            nextHeap = new PriorityQueue<>();
                        heaps.put(nextHeapIndex, nextHeap);
                        if (LOG.isTraceEnabled())
                            LOG.trace("Created heap with index: " + nextHeapIndex);
                    }
                    nextHeap.add(configuration);
                    if (LOG.isTraceEnabled()) {
                        LOG.trace("Added configuration with score " + configuration.getScore() + " to heap: " + nextHeapIndex + ", total size: " + nextHeap.size());
                    }
                    configuration.clearMemory();
                } else {
                    if (LOG.isTraceEnabled())
                        LOG.trace("Cannot apply transition: doesn't meet pre-conditions");
                    // just in case the we run out of both heaps and
                    // analyses, we build this backup heap
                    backupHeap.add(history);
                }
            // does transition meet pre-conditions?
            }
            if (transitionApplied) {
                j++;
            } else {
                LOG.trace("No transitions could be applied: not counting this history as part of the beam");
            }
            // beam width test
            if (j == maxSequences)
                break;
        }
    // next history
    }
    // next atomic index
    // return the best sequences on the heap
    List<ParseConfiguration> bestConfigurations = new ArrayList<>();
    int i = 0;
    if (finalHeap.isEmpty())
        finalHeap = backupHeap;
    while (!finalHeap.isEmpty()) {
        bestConfigurations.add(finalHeap.poll());
        i++;
        if (i >= this.getBeamWidth())
            break;
    }
    if (LOG.isDebugEnabled()) {
        for (ParseConfiguration finalConfiguration : bestConfigurations) {
            LOG.debug(df.format(finalConfiguration.getScore()) + ": " + finalConfiguration.toString());
            LOG.debug("Pos tag sequence: " + finalConfiguration.getPosTagSequence());
            LOG.debug("Transitions: " + finalConfiguration.getTransitions());
            LOG.debug("Decisions: " + finalConfiguration.getDecisions());
            if (LOG.isTraceEnabled()) {
                StringBuilder sb = new StringBuilder();
                for (Decision decision : finalConfiguration.getDecisions()) {
                    sb.append(" * ");
                    sb.append(df.format(decision.getProbability()));
                }
                sb.append(" root ");
                sb.append(finalConfiguration.getTransitions().size());
                LOG.trace(sb.toString());
                sb = new StringBuilder();
                sb.append(" * PosTag sequence score ");
                sb.append(df.format(finalConfiguration.getPosTagSequence().getScore()));
                sb.append(" = ");
                for (PosTaggedToken posTaggedToken : finalConfiguration.getPosTagSequence()) {
                    sb.append(" * ");
                    sb.append(df.format(posTaggedToken.getDecision().getProbability()));
                }
                sb.append(" root ");
                sb.append(finalConfiguration.getPosTagSequence().size());
                LOG.trace(sb.toString());
                sb = new StringBuilder();
                sb.append(" * Token sequence score = ");
                sb.append(df.format(finalConfiguration.getPosTagSequence().getTokenSequence().getScore()));
                LOG.trace(sb.toString());
            }
        }
    }
    return bestConfigurations;
}

Example 2 with PosTagSequence

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

the class PosTagFeatureTester method onNextPosTagSequence.

@Override
public void onNextPosTagSequence(PosTagSequence posTagSequence) throws TalismaneException {
    PosTagSequence currentHistory = new PosTagSequence(posTagSequence.getTokenSequence());
    for (PosTaggedToken posTaggedToken : posTagSequence) {
        if (testWords.contains(posTaggedToken.getToken().getAnalyisText().toLowerCase())) {
            StringBuilder sb = new StringBuilder();
            boolean foundToken = false;
            for (PosTaggedToken taggedToken : posTagSequence) {
                if (taggedToken.equals(posTaggedToken)) {
                    sb.append(" [" + taggedToken.getToken().getOriginalText().replace(' ', '_') + "/" + taggedToken.getTag().toString() + "]");
                    foundToken = true;
                } else if (foundToken) {
                    sb.append(" " + taggedToken.getToken().getOriginalText().replace(' ', '_'));
                } else {
                    sb.append(" " + taggedToken.getToken().getOriginalText().replace(' ', '_') + "/" + taggedToken.getTag().toString());
                }
            }
            LOG.debug(sb.toString());
            String classification = posTaggedToken.getTag().getCode();
            PosTaggerContext context = new PosTaggerContextImpl(posTaggedToken.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: " + posTaggedToken.getToken().getAnalyisText());
                for (FeatureResult<?> result : posTagFeatureResults) {
                    LOG.trace(result.toString());
                }
            }
            for (FeatureResult<?> featureResult : posTagFeatureResults) {
                Map<String, List<String>> classificationMap = featureResultMap.get(featureResult.toString());
                if (classificationMap == null) {
                    classificationMap = new TreeMap<String, List<String>>();
                    featureResultMap.put(featureResult.toString(), classificationMap);
                }
                List<String> sentences = classificationMap.get(classification);
                if (sentences == null) {
                    sentences = new ArrayList<String>();
                    classificationMap.put(classification, sentences);
                }
                sentences.add(sb.toString());
            }
        }
        currentHistory.addPosTaggedToken(posTaggedToken);
    }
}

Example 3 with PosTagSequence

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

the class ParserEvaluator method evaluate.

/**
 * @throws TalismaneException
 *           if an attempt is made to evaluate with a tokeniser but no
 *           pos-tagger
 * @throws IOException
 */
public void evaluate() throws TalismaneException, IOException {
    while (corpusReader.hasNextSentence()) {
        ParseConfiguration realConfiguration = corpusReader.nextConfiguration();
        List<PosTagSequence> posTagSequences = null;
        List<TokenSequence> tokenSequences = null;
        if (tokeniser != null) {
            if (posTagger == null)
                throw new TalismaneException("Cannot evaluate with tokeniser but no pos-tagger");
            Sentence sentence = realConfiguration.getPosTagSequence().getTokenSequence().getSentence();
            // annotate the sentence for pre token filters
            for (SentenceAnnotator annotator : TalismaneSession.get(sessionId).getSentenceAnnotators()) {
                annotator.annotate(sentence);
                if (LOG.isTraceEnabled()) {
                    LOG.trace("TokenFilter: " + annotator);
                    LOG.trace("annotations: " + sentence.getAnnotations());
                }
            }
            tokenSequences = tokeniser.tokenise(sentence);
        } else {
            tokenSequences = new ArrayList<TokenSequence>();
            PosTagSequence posTagSequence = realConfiguration.getPosTagSequence().clonePosTagSequence();
            posTagSequence.removeRoot();
            tokenSequences.add(posTagSequence.getTokenSequence());
        }
        if (posTagger != null) {
            if (posTagger instanceof NonDeterministicPosTagger) {
                NonDeterministicPosTagger nonDeterministicPosTagger = (NonDeterministicPosTagger) posTagger;
                posTagSequences = nonDeterministicPosTagger.tagSentence(tokenSequences);
            } else {
                posTagSequences = new ArrayList<PosTagSequence>();
                PosTagSequence posTagSequence = null;
                posTagSequence = posTagger.tagSentence(tokenSequences.get(0));
                posTagSequences.add(posTagSequence);
            }
        } else {
            PosTagSequence posTagSequence = realConfiguration.getPosTagSequence();
            posTagSequences = new ArrayList<PosTagSequence>();
            posTagSequences.add(posTagSequence);
        }
        for (ParseEvaluationObserver observer : this.observers) {
            observer.onParseStart(realConfiguration, posTagSequences);
        }
        List<ParseConfiguration> guessedConfigurations = null;
        if (parser instanceof NonDeterministicParser) {
            NonDeterministicParser nonDeterministicParser = (NonDeterministicParser) parser;
            guessedConfigurations = nonDeterministicParser.parseSentence(posTagSequences);
        } else {
            ParseConfiguration bestGuess = parser.parseSentence(posTagSequences.get(0));
            guessedConfigurations = new ArrayList<ParseConfiguration>();
            guessedConfigurations.add(bestGuess);
        }
        for (ParseEvaluationObserver observer : this.observers) {
            observer.onParseEnd(realConfiguration, guessedConfigurations);
        }
    }
    for (ParseEvaluationObserver observer : this.observers) {
        observer.onEvaluationComplete();
    }
}

Example 4 with PosTagSequence

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

the class ParserFScoreCalculator method onParseEnd.

@Override
public void onParseEnd(ParseConfiguration realConfiguration, List<ParseConfiguration> guessedConfigurations) throws TalismaneException {
    PosTagSequence posTagSequence = realConfiguration.getPosTagSequence();
    ParseConfiguration bestGuess = guessedConfigurations.get(0);
    int mismatchedTokens = 0;
    for (PosTaggedToken posTaggedToken : posTagSequence) {
        if (!posTaggedToken.getTag().equals(PosTag.ROOT_POS_TAG)) {
            DependencyArc realArc = realConfiguration.getGoverningDependency(posTaggedToken, projective);
            DependencyArc guessedArc = null;
            boolean foundToken = false;
            for (PosTaggedToken guessedToken : bestGuess.getPosTagSequence()) {
                if (guessedToken.getToken().getStartIndex() == posTaggedToken.getToken().getStartIndex()) {
                    if (guessedToken.getToken().isEmpty() && !posTaggedToken.getToken().isEmpty())
                        continue;
                    if (!guessedToken.getToken().isEmpty() && posTaggedToken.getToken().isEmpty())
                        continue;
                    foundToken = true;
                    guessedArc = bestGuess.getGoverningDependency(guessedToken, projective);
                    break;
                }
            }
            if (!foundToken) {
                LOG.info("Mismatched token :" + posTaggedToken.getToken().getOriginalText() + ", index " + posTaggedToken.getToken().getIndex());
                mismatchedTokens += 1;
            }
            String realLabel = realArc == null ? "noHead" : labeledEvaluation ? realArc.getLabel() : "head";
            String guessedLabel = guessedArc == null ? "noHead" : labeledEvaluation ? guessedArc.getLabel() : "head";
            if (realLabel == null || realLabel.length() == 0)
                realLabel = "noLabel";
            if (guessedLabel == null || guessedLabel.length() == 0)
                guessedLabel = "noLabel";
            // should be considered a "no head" rather than "no label"
            if (realArc != null && realArc.getHead().getTag().equals(PosTag.ROOT_POS_TAG) && realLabel.equals("noLabel"))
                realLabel = "noHead";
            if (guessedArc != null && guessedArc.getHead().getTag().equals(PosTag.ROOT_POS_TAG) && guessedLabel.equals("noLabel"))
                guessedLabel = "noHead";
            if (realArc == null || guessedArc == null) {
                fscoreCalculator.increment(realLabel, guessedLabel);
            } else {
                boolean sameHead = realArc.getHead().getToken().getStartIndex() == guessedArc.getHead().getToken().getStartIndex();
                if (sameHead) {
                    fscoreCalculator.increment(realLabel, guessedLabel);
                } else if (guessedLabel.equals("noHead")) {
                    fscoreCalculator.increment(realLabel, "noHead");
                } else if (realArc.getLabel().equals(guessedArc.getLabel())) {
                    fscoreCalculator.increment(realLabel, "wrongHead");
                } else {
                    fscoreCalculator.increment(realLabel, "wrongHeadWrongLabel");
                }
            }
        // have one of the arcs
        }
    // is root tag?
    }
    if ((double) mismatchedTokens / (double) posTagSequence.size() > 0.5) {
        // more than half of the tokens mismatched?
        throw new TalismaneException("Too many mismatched tokens in sentence: " + posTagSequence.getTokenSequence().getSentence().getText());
    }
}

Example 5 with PosTagSequence

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

the class ParserFScoreCalculatorByDistance method onParseEnd.

@Override
public void onParseEnd(ParseConfiguration realConfiguration, List<ParseConfiguration> guessedConfigurations) {
    PosTagSequence posTagSequence = realConfiguration.getPosTagSequence();
    ParseConfiguration bestGuess = guessedConfigurations.get(0);
    for (PosTaggedToken posTaggedToken : posTagSequence) {
        if (posTaggedToken.getTag().equals(PosTag.ROOT_POS_TAG))
            continue;
        DependencyArc realArc = realConfiguration.getGoverningDependency(posTaggedToken);
        int depDistance = realArc.getHead().getToken().getIndex() - realArc.getDependent().getToken().getIndex();
        if (depDistance < 0)
            depDistance = 0 - depDistance;
        FScoreCalculator<String> fscoreCalculator = fscoreByDistanceMap.get(depDistance);
        if (fscoreCalculator == null) {
            fscoreCalculator = new FScoreCalculator<String>(depDistance);
            fscoreByDistanceMap.put(depDistance, fscoreCalculator);
        }
        DependencyArc guessedArc = null;
        if (!hasTokeniser && !hasPosTagger) {
            guessedArc = bestGuess.getGoverningDependency(posTaggedToken);
        } else {
            for (PosTaggedToken guessedToken : bestGuess.getPosTagSequence()) {
                if (guessedToken.getToken().getStartIndex() == posTaggedToken.getToken().getStartIndex()) {
                    guessedArc = bestGuess.getGoverningDependency(guessedToken);
                    break;
                }
            }
        }
        String realLabel = realArc == null ? "noHead" : labeledEvaluation ? realArc.getLabel() : "head";
        String guessedLabel = guessedArc == null ? "noHead" : labeledEvaluation ? guessedArc.getLabel() : "head";
        if (realLabel == null || realLabel.length() == 0)
            realLabel = "noLabel";
        if (guessedLabel == null || guessedLabel.length() == 0)
            guessedLabel = "noLabel";
        // should be considered a "no head" rather than "no label"
        if (realArc != null && realArc.getHead().getTag().equals(PosTag.ROOT_POS_TAG) && realLabel.equals("noLabel"))
            realLabel = "noHead";
        if (guessedArc != null && guessedArc.getHead().getTag().equals(PosTag.ROOT_POS_TAG) && guessedLabel.equals("noLabel"))
            guessedLabel = "noHead";
        if (realLabel.equals(skipLabel))
            return;
        if (realArc == null || guessedArc == null) {
            fscoreCalculator.increment(realLabel, guessedLabel);
        } else {
            boolean sameHead = false;
            if (hasTokeniser || hasPosTagger)
                sameHead = realArc.getHead().getToken().getStartIndex() == guessedArc.getHead().getToken().getStartIndex();
            else
                sameHead = realArc.getHead().equals(guessedArc.getHead());
            if (sameHead) {
                fscoreCalculator.increment(realLabel, guessedLabel);
            } else if (guessedLabel.equals("noHead")) {
                fscoreCalculator.increment(realLabel, "noHead");
            } else if (realArc.getLabel().equals(guessedArc.getLabel())) {
                fscoreCalculator.increment(realLabel, "wrongHead");
            } else {
                fscoreCalculator.increment(realLabel, "wrongHeadWrongLabel");
            }
        }
    }
}