Examples with SemanticGraph edu.stanford.nlp.semgraph.SemanticGraph used on opensource projects

Example 16 with SemanticGraph

use of edu.stanford.nlp.semgraph.SemanticGraph in project CoreNLP by stanfordnlp.

the class CoNLLOutputter method print.

@Override
public void print(Annotation doc, OutputStream target, Options options) throws IOException {
    PrintWriter writer = new PrintWriter(IOUtils.encodedOutputStreamWriter(target, options.encoding));
    // vv A bunch of nonsense to get tokens vv
    if (doc.get(CoreAnnotations.SentencesAnnotation.class) != null) {
        for (CoreMap sentence : doc.get(CoreAnnotations.SentencesAnnotation.class)) {
            if (sentence.get(CoreAnnotations.TokensAnnotation.class) != null) {
                List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
                SemanticGraph depTree = sentence.get(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class);
                for (int i = 0; i < tokens.size(); ++i) {
                    // Newline if applicable
                    if (i > 0) {
                        writer.println();
                    }
                    // Try to get the incoming dependency edge
                    int head = -1;
                    String deprel = null;
                    if (depTree != null) {
                        Set<Integer> rootSet = depTree.getRoots().stream().map(IndexedWord::index).collect(Collectors.toSet());
                        IndexedWord node = depTree.getNodeByIndexSafe(i + 1);
                        if (node != null) {
                            List<SemanticGraphEdge> edgeList = depTree.getIncomingEdgesSorted(node);
                            if (!edgeList.isEmpty()) {
                                assert edgeList.size() == 1;
                                head = edgeList.get(0).getGovernor().index();
                                deprel = edgeList.get(0).getRelation().toString();
                            } else if (rootSet.contains(i + 1)) {
                                head = 0;
                                deprel = "ROOT";
                            }
                        }
                    }
                    // Write the token
                    writer.print(line(i + 1, tokens.get(i), head, deprel));
                }
            }
            writer.println();
            writer.println();
        }
    }
    writer.flush();
}

Example 17 with SemanticGraph

use of edu.stanford.nlp.semgraph.SemanticGraph in project CoreNLP by stanfordnlp.

the class EnglishGrammaticalStructure method postProcessDependencies.

@Override
protected void postProcessDependencies(List<TypedDependency> list) {
    if (DEBUG) {
        printListSorted("At postProcessDependencies:", list);
    }
    SemanticGraph sg = new SemanticGraph(list);
    correctWHAttachment(sg);
    list.clear();
    list.addAll(sg.typedDependencies());
    if (DEBUG) {
        printListSorted("After correcting WH movement", list);
    }
    convertRel(list);
    if (DEBUG) {
        printListSorted("After converting rel:", list);
    }
}

Example 18 with SemanticGraph

use of edu.stanford.nlp.semgraph.SemanticGraph in project CoreNLP by stanfordnlp.

the class UniversalEnglishGrammaticalStructure method expandPrepConjunctions.

/**
   * Expands prepositions with conjunctions such as in the sentence
   * "Bill flies to and from Serbia." by copying the verb resulting
   * in the following relations:
   * <p/>
   * {@code conj:and(flies, flies')}<br/>
   * {@code case(Serbia, to)}<br/>
   * {@code cc(to, and)}<br/>
   * {@code conj(to, from)}<br/>
   * {@code nmod(flies, Serbia)}<br/>
   * {@code nmod(flies', Serbia)}<br/>
   * <p/>
   * The label of the conjunct relation includes the conjunction type
   * because if the verb has multiple cc relations then it can be impossible
   * to infer which coordination marker belongs to which conjuncts.
   *
   * @param sg A SemanticGraph for a sentence
   */
private static void expandPrepConjunctions(SemanticGraph sg) {
    /* Semgrexes require a graph with a root. */
    if (sg.getRoots().isEmpty())
        return;
    SemanticGraph sgCopy = sg.makeSoftCopy();
    SemgrexMatcher matcher = PREP_CONJP_PATTERN.matcher(sgCopy);
    IndexedWord oldGov = null;
    IndexedWord oldCcDep = null;
    List<IndexedWord> conjDeps = Generics.newLinkedList();
    while (matcher.find()) {
        IndexedWord ccDep = matcher.getNode("cc");
        IndexedWord conjDep = matcher.getNode("conj");
        IndexedWord gov = matcher.getNode("gov");
        if (oldGov != null && (!gov.equals(oldGov) || !ccDep.equals(oldCcDep))) {
            expandPrepConjunction(sg, oldGov, conjDeps, oldCcDep);
            conjDeps = Generics.newLinkedList();
        }
        oldCcDep = ccDep;
        oldGov = gov;
        conjDeps.add(conjDep);
    }
    if (oldGov != null) {
        expandPrepConjunction(sg, oldGov, conjDeps, oldCcDep);
    }
}

Example 19 with SemanticGraph

use of edu.stanford.nlp.semgraph.SemanticGraph in project CoreNLP by stanfordnlp.

the class UniversalEnglishGrammaticalStructure method getExtras.

@Override
protected void getExtras(List<TypedDependency> list) {
    SemanticGraph sg = new SemanticGraph(list);
    addRef(sg);
    if (DEBUG) {
        printListSorted("After adding ref:", sg.typedDependencies());
    }
    addExtraNSubj(sg);
    if (DEBUG) {
        printListSorted("After adding extra nsubj:", sg.typedDependencies());
    }
    list.clear();
    list.addAll(sg.typedDependencies());
}

Example 20 with SemanticGraph

use of edu.stanford.nlp.semgraph.SemanticGraph in project CoreNLP by stanfordnlp.

the class StanfordCoreNLPITest method test.

public void test() throws Exception {
    // create a properties that enables all the annotators
    Properties props = new Properties();
    props.setProperty("annotators", "tokenize,ssplit,pos,lemma,ner,parse");
    // run an annotation through the pipeline
    String text = "Dan Ramage is working for\nMicrosoft. He's in Seattle! \n";
    Annotation document = new Annotation(text);
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    pipeline.annotate(document);
    // check that tokens are present
    List<CoreLabel> tokens = document.get(CoreAnnotations.TokensAnnotation.class);
    Assert.assertNotNull(tokens);
    Assert.assertEquals(12, tokens.size());
    // check that sentences are present
    List<CoreMap> sentences = document.get(CoreAnnotations.SentencesAnnotation.class);
    Assert.assertNotNull(sentences);
    Assert.assertEquals(2, sentences.size());
    // check that pos, lemma and ner and parses are present
    for (CoreMap sentence : sentences) {
        List<CoreLabel> sentenceTokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
        Assert.assertNotNull(sentenceTokens);
        for (CoreLabel token : sentenceTokens) {
            Assert.assertNotNull(token.get(CoreAnnotations.PartOfSpeechAnnotation.class));
            Assert.assertNotNull(token.get(CoreAnnotations.LemmaAnnotation.class));
            Assert.assertNotNull(token.get(CoreAnnotations.NamedEntityTagAnnotation.class));
        }
        // check for parse tree
        Assert.assertNotNull(sentence.get(TreeCoreAnnotations.TreeAnnotation.class));
        // check that dependency graph Labels have word()
        SemanticGraph deps = sentence.get(SemanticGraphCoreAnnotations.CollapsedDependenciesAnnotation.class);
        for (IndexedWord vertex : deps.vertexSet()) {
            Assert.assertNotNull(vertex.word());
            Assert.assertEquals(vertex.word(), vertex.value());
        }
    }
    // test pretty print
    StringWriter stringWriter = new StringWriter();
    pipeline.prettyPrint(document, new PrintWriter(stringWriter));
    String result = stringWriter.getBuffer().toString();
    Assert.assertTrue("Tokens are wrong in " + result, StringUtils.find(result, "\\[Text=Dan .*PartOfSpeech=NNP Lemma=Dan NamedEntityTag=PERSON\\]"));
    Assert.assertTrue("Parses are wrong in " + result, result.contains("(NP (PRP He))"));
    Assert.assertTrue("Parses are wrong in " + result, result.contains("(VP (VBZ 's)"));
    Assert.assertTrue("Sentence header is wrong in " + result, result.contains("Sentence #1 (7 tokens)"));
    Assert.assertTrue("Dependencies are wrong in " + result, result.contains("nsubj(working-4, Ramage-2)"));
    // test XML
    ByteArrayOutputStream os = new ByteArrayOutputStream();
    pipeline.xmlPrint(document, os);
    result = new String(os.toByteArray(), "UTF-8");
    Assert.assertTrue("XML header is wrong in " + result, result.startsWith("<?xml version=\"1.0\" encoding=\"UTF-8\"?>"));
    Assert.assertTrue("XML root is wrong in " + result, result.contains("<?xml-stylesheet href=\"CoreNLP-to-HTML.xsl\" type=\"text/xsl\"?>"));
    Assert.assertTrue("XML word info is wrong in " + result, StringUtils.find(result, "<token id=\"2\">\\s*" + "<word>Ramage</word>\\s*" + "<lemma>Ramage</lemma>\\s*" + "<CharacterOffsetBegin>4</CharacterOffsetBegin>\\s*" + "<CharacterOffsetEnd>10</CharacterOffsetEnd>\\s*" + "<POS>NNP</POS>\\s*" + "<NER>PERSON</NER>"));
    Assert.assertTrue("XML dependencies are wrong in " + result, StringUtils.find(result, "<dep type=\"compound\">\\s*<governor idx=\"2\">" + "Ramage</governor>\\s*<dependent idx=\"1\">Dan</dependent>\\s*</dep>"));
}