Examples with CoreMap edu.stanford.nlp.util.CoreMap used on opensource projects

Example 66 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class NERServlet method outputHighlighting.

public void outputHighlighting(PrintWriter out, CRFClassifier classifier, String input) {
    Set<String> labels = classifier.labels();
    String background = classifier.backgroundSymbol();
    List<List<CoreMap>> sentences = classifier.classify(input);
    Map<String, Color> tagToColorMap = NERGUI.makeTagToColorMap(labels, background);
    StringBuilder result = new StringBuilder();
    int lastEndOffset = 0;
    for (List<CoreMap> sentence : sentences) {
        for (CoreMap word : sentence) {
            int beginOffset = word.get(CoreAnnotations.CharacterOffsetBeginAnnotation.class);
            int endOffset = word.get(CoreAnnotations.CharacterOffsetEndAnnotation.class);
            String answer = word.get(CoreAnnotations.AnswerAnnotation.class);
            if (beginOffset > lastEndOffset) {
                result.append(StringEscapeUtils.escapeHtml4(input.substring(lastEndOffset, beginOffset)));
            }
            // Add a color bar for any tagged words
            if (!background.equals(answer)) {
                Color color = tagToColorMap.get(answer);
                result.append("<span style=\"color:#ffffff;background:" + NERGUI.colorToHTML(color) + "\">");
            }
            result.append(StringEscapeUtils.escapeHtml4(input.substring(beginOffset, endOffset)));
            // Turn off the color bar
            if (!background.equals(answer)) {
                result.append("</span>");
            }
            lastEndOffset = endOffset;
        }
    }
    if (lastEndOffset < input.length()) {
        result.append(StringEscapeUtils.escapeHtml4(input.substring(lastEndOffset)));
    }
    result.append("<br><br>");
    result.append("Potential tags:");
    for (String label : tagToColorMap.keySet()) {
        result.append("<br>&nbsp;&nbsp;");
        Color color = tagToColorMap.get(label);
        result.append("<span style=\"color:#ffffff;background:" + NERGUI.colorToHTML(color) + "\">");
        result.append(StringEscapeUtils.escapeHtml4(label));
        result.append("</span>");
    }
    out.print(result.toString());
}

Example 67 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class MachineReading method assignSyntacticHeadToEntities.

private void assignSyntacticHeadToEntities(Annotation corpus) {
    assert (corpus != null);
    assert (corpus.get(SentencesAnnotation.class) != null);
    for (CoreMap sent : corpus.get(SentencesAnnotation.class)) {
        List<CoreLabel> tokens = sent.get(TokensAnnotation.class);
        assert (tokens != null);
        Tree tree = sent.get(TreeAnnotation.class);
        if (MachineReadingProperties.forceGenerationOfIndexSpans) {
            tree.indexSpans(0);
        }
        assert (tree != null);
        if (sent.get(EntityMentionsAnnotation.class) != null) {
            for (EntityMention e : sent.get(EntityMentionsAnnotation.class)) {
                reader.assignSyntacticHead(e, tree, tokens, true);
            }
        }
    }
}

Example 68 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class AceReader method read.

/**
   * Reads in ACE*.apf.xml files and converts them to RelationSentence objects.
   * Note that you probably should call parse() instead.
   *
   * Currently, this ignores document boundaries (the list returned will include
   * sentences from all documents).
   *
   * @param path directory containing ACE files to read (e.g.
   *          "/home/mcclosky/scr/data/ACE2005/english_test"). This can also be
   *          the path to a single file. *
   * @return list of RelationSentence objects
   */
@Override
public Annotation read(String path) throws IOException, SAXException, ParserConfigurationException {
    List<CoreMap> allSentences = new ArrayList<>();
    File basePath = new File(path);
    assert basePath.exists();
    Annotation corpus = new Annotation("");
    if (basePath.isDirectory()) {
        for (File aceFile : IOUtils.iterFilesRecursive(basePath, ".apf.xml")) {
            if (aceFile.getName().endsWith(".UPC1.apf.xml")) {
                continue;
            }
            allSentences.addAll(readDocument(aceFile, corpus));
        }
    } else {
        // in case it's a file
        allSentences.addAll(readDocument(basePath, corpus));
    }
    AnnotationUtils.addSentences(corpus, allSentences);
    // quick stats
    if (VERBOSE) {
        printCounter(entityCounts, "entity mention");
        printCounter(relationCounts, "relation mention");
        printCounter(eventCounts, "event mention");
    }
    for (CoreMap sent : allSentences) {
        // check for entity mentions of the same type that are adjacent
        countAdjacentMentions(sent);
        // count relations between two proper nouns
        countNameRelations(sent);
        // count types of mentions
        countMentionTypes(sent);
    }
    if (VERBOSE) {
        printCounter(adjacentEntityMentions, "adjacent entity mention");
        printCounter(nameRelationCounts, "name relation mention");
        printCounter(mentionTypeCounts, "mention type counts");
    }
    return corpus;
}

Example 69 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class CoreMapSequenceMatcher method getMergedList.

public List<CoreMap> getMergedList(int... groups) {
    List<CoreMap> res = new ArrayList<>();
    int last = 0;
    List<Integer> orderedGroups = CollectionUtils.asList(groups);
    Collections.sort(orderedGroups);
    for (int group : orderedGroups) {
        int groupStart = start(group);
        if (groupStart >= last) {
            res.addAll(elements.subList(last, groupStart));
            int groupEnd = end(group);
            if (groupEnd - groupStart >= 1) {
                CoreMap merged = createMergedChunk(groupStart, groupEnd);
                res.add(merged);
                last = groupEnd;
            }
        }
    }
    res.addAll(elements.subList(last, elements.size()));
    return res;
}

Example 70 with CoreMap

use of edu.stanford.nlp.util.CoreMap in project CoreNLP by stanfordnlp.

the class OpenIEServlet method annotate.

/**
   * Annotate a document (which is usually just a sentence).
   */
public void annotate(StanfordCoreNLP pipeline, Annotation ann) {
    if (ann.get(CoreAnnotations.SentencesAnnotation.class) == null) {
        pipeline.annotate(ann);
    } else {
        if (ann.get(CoreAnnotations.SentencesAnnotation.class).size() == 1) {
            CoreMap sentence = ann.get(CoreAnnotations.SentencesAnnotation.class).get(0);
            for (CoreLabel token : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
                token.remove(NaturalLogicAnnotations.OperatorAnnotation.class);
                token.remove(NaturalLogicAnnotations.PolarityAnnotation.class);
            }
            sentence.remove(NaturalLogicAnnotations.RelationTriplesAnnotation.class);
            sentence.remove(NaturalLogicAnnotations.EntailedSentencesAnnotation.class);
            sentence.remove(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class);
            sentence.remove(SemanticGraphCoreAnnotations.EnhancedDependenciesAnnotation.class);
            sentence.remove(SemanticGraphCoreAnnotations.EnhancedPlusPlusDependenciesAnnotation.class);
            pipeline.annotate(ann);
        }
    }
}