Search in sources :

Example 6 with POSAnnotator

use of edu.illinois.cs.cogcomp.pos.POSAnnotator in project cogcomp-nlp by CogComp.

the class TestDiff method testGetTagValues.

@Test
public void testGetTagValues() {
    POSAnnotator annotator = new POSAnnotator();
    String[] elements = { "#", "$", "''", ",", "-LRB-", "-RRB-", ".", ":", "CC", "CD", "DT", "EX", "FW", "IN", "JJ", "JJR", "JJS", "LS", "MD", "NN", "NNP", "NNPS", "NNS", "PDT", "POS", "PRP", "PRP$", "RB", "RBR", "RBS", "RP", "SYM", "TO", "UH", "VB", "VBD", "VBG", "VBN", "VBP", "VBZ", "WDT", "WP", "WP$", "WRB", "``" };
    Set<String> set = new HashSet(Arrays.asList(elements));
    assertTrue(annotator.getTagValues().equals(set));
}
Also used : POSAnnotator(edu.illinois.cs.cogcomp.pos.POSAnnotator) Test(org.junit.Test)

Example 7 with POSAnnotator

use of edu.illinois.cs.cogcomp.pos.POSAnnotator in project cogcomp-nlp by CogComp.

the class SemEvalMentionReader method initExternalTools.

public void initExternalTools() {
    try {
        _posAnnotator = new POSAnnotator();
        Datastore ds = new Datastore(new ResourceConfigurator().getDefaultConfig());
        File gazetteersResource = ds.getDirectory("org.cogcomp.gazetteers", "gazetteers", 1.3, false);
        _gazetteers = (FlatGazetteers) GazetteersFactory.get(5, gazetteersResource.getPath() + File.separator + "gazetteers", true, Language.English);
        WordNetManager.loadConfigAsClasspathResource(true);
        _wordnet = WordNetManager.getInstance();
        __chunker = new ChunkerAnnotator(true);
        __chunker.initialize(new ChunkerConfigurator().getDefaultConfig());
        Properties stanfordProps = new Properties();
        stanfordProps.put("annotators", "pos, parse");
        stanfordProps.put("parse.originalDependencies", true);
        stanfordProps.put("parse.maxlen", Stanford331Configurator.STFRD_MAX_SENTENCE_LENGTH);
        stanfordProps.put("parse.maxtime", Stanford331Configurator.STFRD_TIME_PER_SENTENCE);
        POSTaggerAnnotator posAnnotator = new POSTaggerAnnotator("pos", stanfordProps);
        ParserAnnotator parseAnnotator = new ParserAnnotator("parse", stanfordProps);
        __stanfordDep = new StanfordDepHandler(posAnnotator, parseAnnotator);
        __mentionAnnotator = new MentionAnnotator("ACE_TYPE");
    } catch (Exception e) {
        e.printStackTrace();
    }
}
Also used : ChunkerAnnotator(edu.illinois.cs.cogcomp.chunker.main.ChunkerAnnotator) POSTaggerAnnotator(edu.stanford.nlp.pipeline.POSTaggerAnnotator) ChunkerConfigurator(edu.illinois.cs.cogcomp.chunker.main.ChunkerConfigurator) Datastore(org.cogcomp.Datastore) ParserAnnotator(edu.stanford.nlp.pipeline.ParserAnnotator) POSAnnotator(edu.illinois.cs.cogcomp.pos.POSAnnotator) MentionAnnotator(org.cogcomp.md.MentionAnnotator) ResourceConfigurator(edu.illinois.cs.cogcomp.core.resources.ResourceConfigurator) File(java.io.File) StanfordDepHandler(edu.illinois.cs.cogcomp.pipeline.handlers.StanfordDepHandler)

Example 8 with POSAnnotator

use of edu.illinois.cs.cogcomp.pos.POSAnnotator in project cogcomp-nlp by CogComp.

the class RelationExtractionTest method testAnnotator.

@Test
public void testAnnotator() {
    File modelDir = null;
    try {
        Datastore ds = new Datastore(new ResourceConfigurator().getDefaultConfig());
        modelDir = ds.getDirectory("org.cogcomp.re", "ACE_TEST_DOCS", 1.1, false);
    } catch (Exception e) {
        e.printStackTrace();
    }
    try {
        ACEReaderWithTrueCaseFixer aceReader = new ACEReaderWithTrueCaseFixer(modelDir.getAbsolutePath() + File.separator + "ACE_TEST_DOCS", false);
        POSAnnotator pos_annotator = new POSAnnotator();
        ChunkerAnnotator chunker = new ChunkerAnnotator(true);
        chunker.initialize(new ChunkerConfigurator().getDefaultConfig());
        Properties stanfordProps = new Properties();
        stanfordProps.put("annotators", "pos, parse");
        stanfordProps.put("parse.originalDependencies", true);
        stanfordProps.put("parse.maxlen", Stanford331Configurator.STFRD_MAX_SENTENCE_LENGTH);
        stanfordProps.put("parse.maxtime", Stanford331Configurator.STFRD_TIME_PER_SENTENCE);
        POSTaggerAnnotator posAnnotator = new POSTaggerAnnotator("pos", stanfordProps);
        ParserAnnotator parseAnnotator = new ParserAnnotator("parse", stanfordProps);
        StanfordDepHandler stanfordDepHandler = new StanfordDepHandler(posAnnotator, parseAnnotator);
        MentionAnnotator mentionAnnotator = new MentionAnnotator("ACE_TYPE");
        RelationAnnotator relationAnnotator = new RelationAnnotator();
        for (TextAnnotation ta : aceReader) {
            ta.addView(pos_annotator);
            chunker.addView(ta);
            stanfordDepHandler.addView(ta);
            mentionAnnotator.addView(ta);
            relationAnnotator.addView(ta);
            View mentionView = ta.getView(ViewNames.MENTION);
            assertTrue(mentionView.getConstituents().size() > 0);
            View relationView = ta.getView(ViewNames.RELATION);
            assertTrue(relationView.getRelations().size() > 0);
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}
Also used : ACEReaderWithTrueCaseFixer(edu.illinois.cs.cogcomp.nlp.corpusreaders.ACEReaderWithTrueCaseFixer) ChunkerConfigurator(edu.illinois.cs.cogcomp.chunker.main.ChunkerConfigurator) ParserAnnotator(edu.stanford.nlp.pipeline.ParserAnnotator) POSAnnotator(edu.illinois.cs.cogcomp.pos.POSAnnotator) MentionAnnotator(org.cogcomp.md.MentionAnnotator) ResourceConfigurator(edu.illinois.cs.cogcomp.core.resources.ResourceConfigurator) Properties(java.util.Properties) RelationAnnotator(org.cogcomp.re.RelationAnnotator) View(edu.illinois.cs.cogcomp.core.datastructures.textannotation.View) ChunkerAnnotator(edu.illinois.cs.cogcomp.chunker.main.ChunkerAnnotator) POSTaggerAnnotator(edu.stanford.nlp.pipeline.POSTaggerAnnotator) Datastore(org.cogcomp.Datastore) TextAnnotation(edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation) File(java.io.File) StanfordDepHandler(edu.illinois.cs.cogcomp.pipeline.handlers.StanfordDepHandler) Test(org.junit.Test)

Example 9 with POSAnnotator

use of edu.illinois.cs.cogcomp.pos.POSAnnotator in project cogcomp-nlp by CogComp.

the class ExampleUsage method SemEvalAnnotate.

public static void SemEvalAnnotate() {
    String text = "People have been moving back into downtown.";
    String corpus = "semeval";
    String textId = "001";
    // Create a TextAnnotation From Text
    TextAnnotationBuilder stab = new TokenizerTextAnnotationBuilder(new StatefulTokenizer());
    TextAnnotation ta = stab.createTextAnnotation(corpus, textId, text);
    POSAnnotator pos_annotator = new POSAnnotator();
    ChunkerAnnotator chunker = new ChunkerAnnotator(true);
    chunker.initialize(new ChunkerConfigurator().getDefaultConfig());
    Properties stanfordProps = new Properties();
    stanfordProps.put("annotators", "pos, parse");
    stanfordProps.put("parse.originalDependencies", true);
    stanfordProps.put("parse.maxlen", Stanford331Configurator.STFRD_MAX_SENTENCE_LENGTH);
    stanfordProps.put("parse.maxtime", Stanford331Configurator.STFRD_TIME_PER_SENTENCE);
    POSTaggerAnnotator posAnnotator = new POSTaggerAnnotator("pos", stanfordProps);
    ParserAnnotator parseAnnotator = new ParserAnnotator("parse", stanfordProps);
    StanfordDepHandler stanfordDepHandler = new StanfordDepHandler(posAnnotator, parseAnnotator);
    String modelPath = "";
    FlatGazetteers gazetteers = null;
    try {
        ta.addView(pos_annotator);
        chunker.addView(ta);
        stanfordDepHandler.addView(ta);
        Datastore ds = new Datastore(new ResourceConfigurator().getDefaultConfig());
        File model = ds.getDirectory("org.cogcomp.re", "SEMEVAL", 1.1, false);
        modelPath = model.getPath();
        File gazetteersResource = ds.getDirectory("org.cogcomp.gazetteers", "gazetteers", 1.3, false);
        gazetteers = (FlatGazetteers) GazetteersFactory.get(5, gazetteersResource.getPath() + File.separator + "gazetteers", true, Language.English);
        WordNetManager.loadConfigAsClasspathResource(true);
        WordNetManager wordnet = WordNetManager.getInstance();
        View annotatedTokenView = new SpanLabelView("RE_ANNOTATED", ta);
        for (Constituent co : ta.getView(ViewNames.TOKENS).getConstituents()) {
            Constituent c = co.cloneForNewView("RE_ANNOTATED");
            for (String s : co.getAttributeKeys()) {
                c.addAttribute(s, co.getAttribute(s));
            }
            c.addAttribute("WORDNETTAG", BIOFeatureExtractor.getWordNetTags(wordnet, c));
            c.addAttribute("WORDNETHYM", BIOFeatureExtractor.getWordNetHyms(wordnet, c));
            annotatedTokenView.addConstituent(c);
        }
        ta.addView("RE_ANNOTATED", annotatedTokenView);
    } catch (Exception e) {
        e.printStackTrace();
    }
    Constituent source = new Constituent("first", "Mention", ta, 0, 1);
    Constituent target = new Constituent("second", "Mention", ta, 6, 7);
    source.addAttribute("GAZ", gazetteers.annotatePhrase(source));
    target.addAttribute("GAZ", gazetteers.annotatePhrase(target));
    Relation relation = new Relation("TEST", source, target, 1.0f);
    String prefix = modelPath + File.separator + "SEMEVAL" + File.separator + "SEMEVAL";
    semeval_relation_classifier classifier = new semeval_relation_classifier(prefix + ".lc", prefix + ".lex");
    String tag = classifier.discreteValue(relation);
    System.out.println(tag);
}
Also used : ChunkerConfigurator(edu.illinois.cs.cogcomp.chunker.main.ChunkerConfigurator) TextAnnotationBuilder(edu.illinois.cs.cogcomp.annotation.TextAnnotationBuilder) TokenizerTextAnnotationBuilder(edu.illinois.cs.cogcomp.nlp.utility.TokenizerTextAnnotationBuilder) ParserAnnotator(edu.stanford.nlp.pipeline.ParserAnnotator) POSAnnotator(edu.illinois.cs.cogcomp.pos.POSAnnotator) ResourceConfigurator(edu.illinois.cs.cogcomp.core.resources.ResourceConfigurator) Properties(java.util.Properties) LbjGen.semeval_relation_classifier(org.cogcomp.re.LbjGen.semeval_relation_classifier) FlatGazetteers(edu.illinois.cs.cogcomp.ner.ExpressiveFeatures.FlatGazetteers) ChunkerAnnotator(edu.illinois.cs.cogcomp.chunker.main.ChunkerAnnotator) POSTaggerAnnotator(edu.stanford.nlp.pipeline.POSTaggerAnnotator) WordNetManager(edu.illinois.cs.cogcomp.edison.utilities.WordNetManager) Datastore(org.cogcomp.Datastore) TokenizerTextAnnotationBuilder(edu.illinois.cs.cogcomp.nlp.utility.TokenizerTextAnnotationBuilder) StatefulTokenizer(edu.illinois.cs.cogcomp.nlp.tokenizer.StatefulTokenizer) File(java.io.File) StanfordDepHandler(edu.illinois.cs.cogcomp.pipeline.handlers.StanfordDepHandler)

Example 10 with POSAnnotator

use of edu.illinois.cs.cogcomp.pos.POSAnnotator in project cogcomp-nlp by CogComp.

the class ExampleUsage method AnnotatorExample.

public static void AnnotatorExample() {
    String text = "He went to Chicago after his Father moved there.";
    String corpus = "story";
    String textId = "001";
    // Create a TextAnnotation From Text
    TextAnnotationBuilder stab = new TokenizerTextAnnotationBuilder(new StatefulTokenizer());
    TextAnnotation ta = stab.createTextAnnotation(corpus, textId, text);
    POSAnnotator pos_annotator = new POSAnnotator();
    ChunkerAnnotator chunker = new ChunkerAnnotator(true);
    chunker.initialize(new ChunkerConfigurator().getDefaultConfig());
    Properties stanfordProps = new Properties();
    stanfordProps.put("annotators", "pos, parse");
    stanfordProps.put("parse.originalDependencies", true);
    stanfordProps.put("parse.maxlen", Stanford331Configurator.STFRD_MAX_SENTENCE_LENGTH);
    stanfordProps.put("parse.maxtime", Stanford331Configurator.STFRD_TIME_PER_SENTENCE);
    POSTaggerAnnotator posAnnotator = new POSTaggerAnnotator("pos", stanfordProps);
    ParserAnnotator parseAnnotator = new ParserAnnotator("parse", stanfordProps);
    StanfordDepHandler stanfordDepHandler = new StanfordDepHandler(posAnnotator, parseAnnotator);
    RelationAnnotator relationAnnotator = new RelationAnnotator();
    try {
        ta.addView(pos_annotator);
        chunker.addView(ta);
        stanfordDepHandler.addView(ta);
        relationAnnotator.addView(ta);
    } catch (Exception e) {
        e.printStackTrace();
    }
    View mentionView = ta.getView(ViewNames.MENTION);
    List<Constituent> predictedMentions = mentionView.getConstituents();
    List<Relation> predictedRelations = mentionView.getRelations();
    for (Relation r : predictedRelations) {
        IOHelper.printRelation(r);
    }
}
Also used : ChunkerConfigurator(edu.illinois.cs.cogcomp.chunker.main.ChunkerConfigurator) TextAnnotationBuilder(edu.illinois.cs.cogcomp.annotation.TextAnnotationBuilder) TokenizerTextAnnotationBuilder(edu.illinois.cs.cogcomp.nlp.utility.TokenizerTextAnnotationBuilder) ParserAnnotator(edu.stanford.nlp.pipeline.ParserAnnotator) POSAnnotator(edu.illinois.cs.cogcomp.pos.POSAnnotator) Properties(java.util.Properties) ChunkerAnnotator(edu.illinois.cs.cogcomp.chunker.main.ChunkerAnnotator) POSTaggerAnnotator(edu.stanford.nlp.pipeline.POSTaggerAnnotator) TokenizerTextAnnotationBuilder(edu.illinois.cs.cogcomp.nlp.utility.TokenizerTextAnnotationBuilder) StatefulTokenizer(edu.illinois.cs.cogcomp.nlp.tokenizer.StatefulTokenizer) StanfordDepHandler(edu.illinois.cs.cogcomp.pipeline.handlers.StanfordDepHandler)

Aggregations

POSAnnotator (edu.illinois.cs.cogcomp.pos.POSAnnotator)20 TextAnnotation (edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation)12 TextAnnotationBuilder (edu.illinois.cs.cogcomp.annotation.TextAnnotationBuilder)7 ChunkerAnnotator (edu.illinois.cs.cogcomp.chunker.main.ChunkerAnnotator)7 StatefulTokenizer (edu.illinois.cs.cogcomp.nlp.tokenizer.StatefulTokenizer)7 TokenizerTextAnnotationBuilder (edu.illinois.cs.cogcomp.nlp.utility.TokenizerTextAnnotationBuilder)7 StanfordDepHandler (edu.illinois.cs.cogcomp.pipeline.handlers.StanfordDepHandler)7 POSTaggerAnnotator (edu.stanford.nlp.pipeline.POSTaggerAnnotator)7 ParserAnnotator (edu.stanford.nlp.pipeline.ParserAnnotator)7 Properties (java.util.Properties)7 ChunkerConfigurator (edu.illinois.cs.cogcomp.chunker.main.ChunkerConfigurator)6 Constituent (edu.illinois.cs.cogcomp.core.datastructures.textannotation.Constituent)6 MentionAnnotator (org.cogcomp.md.MentionAnnotator)6 AnnotatorException (edu.illinois.cs.cogcomp.annotation.AnnotatorException)5 Test (org.junit.Test)5 View (edu.illinois.cs.cogcomp.core.datastructures.textannotation.View)4 ResourceConfigurator (edu.illinois.cs.cogcomp.core.resources.ResourceConfigurator)4 ResourceManager (edu.illinois.cs.cogcomp.core.utilities.configuration.ResourceManager)4 ACEReader (edu.illinois.cs.cogcomp.nlp.corpusreaders.ACEReader)3 InvalidEndpointException (io.minio.errors.InvalidEndpointException)3