Examples with HasWord edu.stanford.nlp.ling.HasWord used on opensource projects

Example 6 with HasWord

use of edu.stanford.nlp.ling.HasWord in project CoreNLP by stanfordnlp.

the class DependencyParser method parseTextFile.

private void parseTextFile(BufferedReader input, PrintWriter output) {
    DocumentPreprocessor preprocessor = new DocumentPreprocessor(input);
    preprocessor.setSentenceFinalPuncWords(config.tlp.sentenceFinalPunctuationWords());
    preprocessor.setEscaper(config.escaper);
    preprocessor.setSentenceDelimiter(config.sentenceDelimiter);
    preprocessor.setTokenizerFactory(config.tlp.getTokenizerFactory());
    Timing timer = new Timing();
    MaxentTagger tagger = new MaxentTagger(config.tagger);
    List<List<TaggedWord>> tagged = new ArrayList<>();
    for (List<HasWord> sentence : preprocessor) {
        tagged.add(tagger.tagSentence(sentence));
    }
    System.err.printf("Tagging completed in %.2f sec.%n", timer.stop() / 1000.0);
    timer.start();
    int numSentences = 0;
    for (List<TaggedWord> taggedSentence : tagged) {
        GrammaticalStructure parse = predict(taggedSentence);
        Collection<TypedDependency> deps = parse.typedDependencies();
        for (TypedDependency dep : deps) output.println(dep);
        output.println();
        numSentences++;
    }
    long millis = timer.stop();
    double seconds = millis / 1000.0;
    System.err.printf("Parsed %d sentences in %.2f seconds (%.2f sents/sec).%n", numSentences, seconds, numSentences / seconds);
}

Example 7 with HasWord

use of edu.stanford.nlp.ling.HasWord in project CoreNLP by stanfordnlp.

the class DependencyParserDemo method main.

public static void main(String[] args) {
    String modelPath = DependencyParser.DEFAULT_MODEL;
    String taggerPath = "edu/stanford/nlp/models/pos-tagger/english-left3words/english-left3words-distsim.tagger";
    for (int argIndex = 0; argIndex < args.length; ) {
        switch(args[argIndex]) {
            case "-tagger":
                taggerPath = args[argIndex + 1];
                argIndex += 2;
                break;
            case "-model":
                modelPath = args[argIndex + 1];
                argIndex += 2;
                break;
            default:
                throw new RuntimeException("Unknown argument " + args[argIndex]);
        }
    }
    String text = "I can almost always tell when movies use fake dinosaurs.";
    MaxentTagger tagger = new MaxentTagger(taggerPath);
    DependencyParser parser = DependencyParser.loadFromModelFile(modelPath);
    DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(text));
    for (List<HasWord> sentence : tokenizer) {
        List<TaggedWord> tagged = tagger.tagSentence(sentence);
        GrammaticalStructure gs = parser.predict(tagged);
        // Print typed dependencies
        log.info(gs);
    }
}

Example 8 with HasWord

use of edu.stanford.nlp.ling.HasWord in project CoreNLP by stanfordnlp.

the class ScrollableTreeJPanel method renderRows.

private void renderRows(Graphics2D g2, FontMetrics fM, Color defaultColor2) {
    double nodeHeight = fM.getHeight();
    double layerMultiplier = (1.0 + belowLineSkip + aboveLineSkip + parentSkip);
    double layerHeight = nodeHeight * layerMultiplier;
    //Draw the yield
    List<HasWord> sentence = tree.yieldHasWord();
    for (int i = 0; i < sentence.size(); i++) {
        g2.drawString(sentence.get(i).word(), yieldOffsets[i], (float) (yieldHeight + layerHeight));
    }
    //Greedily draw the constituents
    final float rowOrigin = (float) (yieldHeight + 2.0 * layerHeight);
    List<List<IntPair>> rows = new ArrayList<>();
    for (Constituent c : diffConstituents) {
        for (int rowIdx = 0; rowIdx < diffConstituents.size(); rowIdx++) {
            float rowHeight = rowOrigin + (float) (rowIdx * layerHeight);
            int ext = (c.end() == (yieldOffsets.length - 1)) ? 0 : 1;
            if (rowIdx >= rows.size()) {
                rows.add(new ArrayList<>());
                rows.get(rowIdx).add(new IntPair(c.start(), c.end()));
                double nodeWidth = fM.stringWidth(c.value());
                g2.drawString(c.value(), yieldOffsets[c.start()], rowHeight);
                try {
                    g2.drawLine((int) (yieldOffsets[c.start()] + nodeWidth) + 10, (int) rowHeight, (int) (yieldOffsets[c.end() + ext]) - 15, (int) rowHeight);
                } catch (ArrayIndexOutOfBoundsException e) {
                // This happens if yield of two compared trees do not match.  Just ignore it for now
                // System.err.printf("yieldOffsets.length is %d, c.start() is %d, c.end() is %d, ext is %d%n", yieldOffsets.length, c.start(), c.end(), ext);
                }
                break;
            } else {
                boolean foundOverlap = false;
                for (IntPair span : rows.get(rowIdx)) {
                    if (doesOverlap(c, span)) {
                        foundOverlap = true;
                        break;
                    }
                }
                if (!foundOverlap) {
                    rows.get(rowIdx).add(new IntPair(c.start(), c.end()));
                    double nodeWidth = fM.stringWidth(c.value());
                    g2.drawString(c.value(), yieldOffsets[c.start()], rowHeight);
                    g2.drawLine((int) (yieldOffsets[c.start()] + nodeWidth) + 10, (int) rowHeight, (int) (yieldOffsets[c.end() + ext]) - 15, (int) rowHeight);
                    break;
                }
            }
        }
    }
}

Example 9 with HasWord

use of edu.stanford.nlp.ling.HasWord in project CoreNLP by stanfordnlp.

the class UniversalSemanticHeadFinder method isVerbalAuxiliary.

private boolean isVerbalAuxiliary(Tree preterminal, Set<String> verbalSet, boolean allowJustTagMatch) {
    if (preterminal.isPreTerminal()) {
        Label kidLabel = preterminal.label();
        String tag = null;
        if (kidLabel instanceof HasTag) {
            tag = ((HasTag) kidLabel).tag();
        }
        if (tag == null) {
            tag = preterminal.value();
        }
        Label wordLabel = preterminal.firstChild().label();
        String word = null;
        if (wordLabel instanceof HasWord) {
            word = ((HasWord) wordLabel).word();
        }
        if (word == null) {
            word = wordLabel.value();
        }
        if (DEBUG) {
            log.info("Checking " + preterminal.value() + " head is " + word + '/' + tag);
        }
        String lcWord = word.toLowerCase();
        if (allowJustTagMatch && unambiguousAuxiliaryTags.contains(tag) || verbalTags.contains(tag) && verbalSet.contains(lcWord)) {
            if (DEBUG) {
                log.info("isAuxiliary found desired type of aux");
            }
            return true;
        }
    }
    return false;
}

Example 10 with HasWord

use of edu.stanford.nlp.ling.HasWord in project CoreNLP by stanfordnlp.

the class SpanishXMLTreeReader method buildWordNode.

/**
   * Build a parse tree node corresponding to the word in the given XML node.
   */
private Tree buildWordNode(Node root) {
    Element eRoot = (Element) root;
    String posStr = getPOS(eRoot);
    posStr = treeNormalizer.normalizeNonterminal(posStr);
    String lemma = eRoot.getAttribute(ATTR_LEMMA);
    String word = getWord(eRoot);
    String leafStr = treeNormalizer.normalizeTerminal(word);
    Tree leafNode = treeFactory.newLeaf(leafStr);
    if (leafNode.label() instanceof HasWord)
        ((HasWord) leafNode.label()).setWord(leafStr);
    if (leafNode.label() instanceof HasLemma && lemma != null)
        ((HasLemma) leafNode.label()).setLemma(lemma);
    List<Tree> kids = new ArrayList<>();
    kids.add(leafNode);
    Tree t = treeFactory.newTreeNode(posStr, kids);
    if (t.label() instanceof HasTag)
        ((HasTag) t.label()).setTag(posStr);
    return t;
}