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

Example 76 with IndexedWord

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

the class CoNLLUDocumentWriter method printSemanticGraph.

public String printSemanticGraph(SemanticGraph sg, boolean unescapeParenthesis) {
    StringBuilder sb = new StringBuilder();
    /* Print comments. */
    for (String comment : sg.getComments()) {
        sb.append(comment).append("\n");
    }
    for (IndexedWord token : sg.vertexListSorted()) {
        /* Check for multiword tokens. */
        if (token.containsKey(CoreAnnotations.CoNLLUTokenSpanAnnotation.class)) {
            IntPair tokenSpan = token.get(CoreAnnotations.CoNLLUTokenSpanAnnotation.class);
            if (tokenSpan.getSource() == token.index()) {
                String range = String.format("%d-%d", tokenSpan.getSource(), tokenSpan.getTarget());
                sb.append(String.format("%s\t%s\t_\t_\t_\t_\t_\t_\t_\t_%n", range, token.originalText()));
            }
        }
        /* Try to find main governor and additional dependencies. */
        int govIdx = -1;
        GrammaticalRelation reln = null;
        HashMap<Integer, String> additionalDeps = new HashMap<>();
        for (IndexedWord parent : sg.getParents(token)) {
            SemanticGraphEdge edge = sg.getEdge(parent, token);
            if (govIdx == -1 && !edge.isExtra()) {
                govIdx = parent.index();
                reln = edge.getRelation();
            } else {
                additionalDeps.put(parent.index(), edge.getRelation().toString());
            }
        }
        String additionalDepsString = CoNLLUUtils.toExtraDepsString(additionalDeps);
        String word = token.word();
        String featuresString = CoNLLUUtils.toFeatureString(token.get(CoreAnnotations.CoNLLUFeats.class));
        String pos = token.getString(CoreAnnotations.PartOfSpeechAnnotation.class, "_");
        String upos = token.getString(CoreAnnotations.CoarseTagAnnotation.class, "_");
        String misc = token.getString(CoreAnnotations.CoNLLUMisc.class, "_");
        String lemma = token.getString(CoreAnnotations.LemmaAnnotation.class, "_");
        String relnName = reln == null ? "_" : reln.toString();
        /* Root. */
        if (govIdx == -1 && sg.getRoots().contains(token)) {
            govIdx = 0;
            relnName = GrammaticalRelation.ROOT.toString();
        }
        if (unescapeParenthesis) {
            word = word.replaceAll(LRB_PATTERN, "(");
            word = word.replaceAll(RRB_PATTERN, ")");
            lemma = lemma.replaceAll(LRB_PATTERN, "(");
            lemma = lemma.replaceAll(RRB_PATTERN, ")");
        }
        sb.append(String.format("%d\t%s\t%s\t%s\t%s\t%s\t%d\t%s\t%s\t%s%n", token.index(), word, lemma, upos, pos, featuresString, govIdx, relnName, additionalDepsString, misc));
    }
    sb.append("\n");
    return sb.toString();
}

Example 77 with IndexedWord

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

the class UniversalDependenciesFeatureAnnotator method getGraphFeatures.

private static HashMap<String, String> getGraphFeatures(SemanticGraph sg, IndexedWord word) {
    HashMap<String, String> features = new HashMap<>();
    /* Determine the case of "you". */
    if (word.tag().equals("PRP") && (word.value().equalsIgnoreCase("you") || word.value().equalsIgnoreCase("it"))) {
        features.put("Case", pronounCase(sg, word));
    }
    /* Determine the person of "was". */
    if (word.tag().equals("VBD") && word.value().equalsIgnoreCase("was")) {
        String person = wasPerson(sg, word);
        if (person != null) {
            features.put("Person", person);
        }
    }
    /* Determine features of relative and interrogative pronouns. */
    features.putAll(getRelAndIntPronFeatures(sg, word));
    /* Determine features of gerunds and present participles. */
    if (word.tag().equals("VBG")) {
        if (hasBeAux(sg, word)) {
            features.put("VerbForm", "Part");
            features.put("Tense", "Pres");
        } else {
            features.put("VerbForm", "Ger");
        }
    }
    /* Determine whether reflexive pronoun is reflexive or intensive. */
    if (word.value().matches(SELF_REGEX) && word.tag().equals("PRP")) {
        IndexedWord parent = sg.getParent(word);
        if (parent != null) {
            SemanticGraphEdge edge = sg.getEdge(parent, word);
            if (edge.getRelation() != UniversalEnglishGrammaticalRelations.NP_ADVERBIAL_MODIFIER) {
                features.put("Case", "Acc");
                features.put("Reflex", "Yes");
            }
        }
    }
    /* Voice feature. */
    if (word.tag().equals("VBN")) {
        if (sg.hasChildWithReln(word, UniversalEnglishGrammaticalRelations.AUX_PASSIVE_MODIFIER)) {
            features.put("Voice", "Pass");
        }
    }
    return features;
}

Example 78 with IndexedWord

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

the class UniversalDependenciesFeatureAnnotator method main.

public static void main(String[] args) throws IOException {
    if (args.length < 2) {
        log.info("Usage: ");
        log.info("java ");
        log.info(UniversalDependenciesFeatureAnnotator.class.getCanonicalName());
        log.info(" CoNLL-U_file tree_file [-addUPOS -escapeParenthesis]");
        return;
    }
    String coNLLUFile = args[0];
    String treeFile = args[1];
    boolean addUPOS = false;
    boolean escapeParens = false;
    for (int i = 2; i < args.length; i++) {
        if (args[i].equals("-addUPOS")) {
            addUPOS = true;
        } else if (args[i].equals("-escapeParenthesis")) {
            escapeParens = true;
        }
    }
    UniversalDependenciesFeatureAnnotator featureAnnotator = new UniversalDependenciesFeatureAnnotator();
    Reader r = IOUtils.readerFromString(coNLLUFile);
    CoNLLUDocumentReader depReader = new CoNLLUDocumentReader();
    CoNLLUDocumentWriter depWriter = new CoNLLUDocumentWriter();
    Iterator<SemanticGraph> it = depReader.getIterator(r);
    Iterator<Tree> treeIt = treebankIterator(treeFile);
    while (it.hasNext()) {
        SemanticGraph sg = it.next();
        Tree t = treeIt.next();
        if (t == null || t.yield().size() != sg.size()) {
            StringBuilder sentenceSb = new StringBuilder();
            for (IndexedWord word : sg.vertexListSorted()) {
                sentenceSb.append(word.get(CoreAnnotations.TextAnnotation.class));
                sentenceSb.append(' ');
            }
            throw new RuntimeException("CoNLL-U file and tree file are not aligned. \n" + "Sentence: " + sentenceSb + '\n' + "Tree: " + t.pennString());
        }
        featureAnnotator.addFeatures(sg, t, true, addUPOS);
        System.out.print(depWriter.printSemanticGraph(sg, !escapeParens));
    }
}

Example 79 with IndexedWord

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

the class UniversalDependenciesFeatureAnnotator method pronounCase.

/**
   * Determine the case of the pronoun "you" or "it".
   */
private static String pronounCase(SemanticGraph sg, IndexedWord word) {
    word = sg.getNodeByIndex(word.index());
    IndexedWord parent = sg.getParent(word);
    if (parent != null) {
        SemanticGraphEdge edge = sg.getEdge(parent, word);
        if (edge != null) {
            if (UniversalEnglishGrammaticalRelations.OBJECT.isAncestor(edge.getRelation())) {
                /* "you" is an object. */
                return "Acc";
            } else if (UniversalEnglishGrammaticalRelations.NOMINAL_MODIFIER.isAncestor(edge.getRelation()) || edge.getRelation() == GrammaticalRelation.ROOT) {
                if (sg.hasChildWithReln(word, UniversalEnglishGrammaticalRelations.CASE_MARKER)) {
                    /* "you" is the head of a prepositional phrase. */
                    return "Acc";
                }
            }
        }
    }
    return "Nom";
}

Example 80 with IndexedWord

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

the class UniversalDependenciesFeatureAnnotator method getRelAndIntPronFeatures.

/**
   * Extracts features from relative and interrogative pronouns.
   */
private static HashMap<String, String> getRelAndIntPronFeatures(SemanticGraph sg, IndexedWord word) {
    HashMap<String, String> features = new HashMap<>();
    if (word.tag().startsWith("W")) {
        boolean isRel = false;
        IndexedWord parent = sg.getParent(word);
        if (parent != null) {
            IndexedWord parentParent = sg.getParent(parent);
            if (parentParent != null) {
                SemanticGraphEdge edge = sg.getEdge(parentParent, parent);
                isRel = edge.getRelation().equals(UniversalEnglishGrammaticalRelations.RELATIVE_CLAUSE_MODIFIER);
            }
        }
        if (isRel) {
            features.put("PronType", "Rel");
        } else {
            if (word.value().equalsIgnoreCase("that")) {
                features.put("PronType", "Dem");
            } else {
                features.put("PronType", "Int");
            }
        }
    }
    return features;
}