Package edu.washington.cs.knowitall.nlp

Examples of edu.washington.cs.knowitall.nlp.ChunkedSentence

23
24
25
26
27
28
29
30
31
32
    @Before
    public void setUp() throws Exception {
        String[] tokens = "John Smith was born in Detroit in March .".split(" ");
        String[] pos = "NNP NNP VBD VBN IN NNP IN NNP .".split(" ");
        String[] np = "B-NP I-NP O O O B-NP O B-NP O".split(" ");
        sent = new ChunkedSentence(tokens, pos, np);
        sameSent = sent.clone();
        tokens[0] = "Joe";
        otherSent = new ChunkedSentence(tokens, pos, np);
    }
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
    List<String> tokens = Arrays.asList(tokensStr.split(" "));
    List<String> posTags = Arrays.asList(posTagsStr.split(" "));
    List<String> npChunkTags = new ArrayList<String>(posTags.size());
    for (int i = 0; i < posTags.size(); i++) npChunkTags.add("O");
   
    ChunkedSentence sent = new ChunkedSentence(tokens, posTags, npChunkTags);
    ChunkedExtraction extr = new ChunkedExtraction(sent, new Range(0, posTags.size()));
   
    NormalizedField normField = normalizer.normalizeField(extr);
    String resultStr = normField.toString();
    assertEquals(expectedStr, resultStr);
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
    public void setUp() throws Exception {
       
        List<String> tokens = Arrays.asList("The President of the United States and black shoes and blue".split(" "));
        List<String> posTags = Arrays.asList("DT NNP IN DT NNP NNP CC JJ NNS CC JJ".split(" "));
        List<String> npChunkTags = Arrays.asList("O O O O O O O O O O O".split(" "));
        sent = new ChunkedSentence(tokens, posTags, npChunkTags);
       
        field1 = new ChunkedExtraction(sent, new Range(0, 6));
        field2 = new ChunkedExtraction(sent, new Range(7, 2));
        field3 = new ChunkedExtraction(sent, new Range(10, 1));
       
View Full Code Here
60
61
62
63
64
65
66
    public static ChunkedSentence asSentence(String tokensStr, String posTagsStr, String npChunkTagsStr) throws Exception {
        String[] tokens = tokensStr.split(" ");
        String[] posTags = posTagsStr.split(" ");
        String[] npChunkTags = npChunkTagsStr.split(" ");
        return new ChunkedSentence(tokens, posTags, npChunkTags);
    }
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
    private String prep = "[IN_pos TO_pos]";


    @Before
    public void setUp() throws Exception {
        sent1 = new ChunkedSentence(
                new String[] { "Obama", "was", "a", "professor", "of", "Law", "at", "UChicago", "." },
                new String[] { "NNP", "VBD", "DT", "NN", "IN", "NN", "IN", "NNP", "." },
                new String[] { "B-NP", "O", "B-NP", "I-NP", "I-NP", "I-NP", "O", "B-NP", "O" }
        );
    }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
    e3.addMapper(new MergeOverlappingMapper());
  }
 
  @Test
  public void testMerge() throws Exception {
    ChunkedSentence sent = new ChunkedSentence(
      new String[] { "He", "wants", "to", "go", "to", "the", "store", "." },
            new String[] { "PRP", "VBZ", "TO", "VB", "TO", "DT", "NN", "." },
            new String[] { "B-NP", "O", "O", "O", "O", "B-NP", "I-NP", "O" }
        );
   
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
        expectedRanges.add(new Range(16, 2)); // the wake
        expectedRanges.add(new Range(19, 3)); // this unthinkable tragedy

        OpenNlpChunkedSentenceParser reader = new OpenNlpChunkedSentenceParser();
        reader.attachOfs(false);
        ChunkedSentence sent = reader.parseSentence(sentStr);

        ArrayList<Range> gotRanges = new ArrayList<Range>();
        Iterables.addAll(gotRanges, sent.getNpChunkRanges());

        assertEquals(expectedLength, sent.getLength());
        assertArrayEquals(expectedPos, sent.getPosTags().toArray());
        assertArrayEquals(expectedToks, sent.getTokens().toArray());
        assertEquals(expectedRanges, gotRanges);


    }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
   
    private static void addSentExtr(String a, String b, String c,
            int xs, int xl, int rs, int rl, int ys, int yl, double conf,
            String docId) throws Exception {
       
        ChunkedSentence sent = toSent(a,b,c);
        sentences.add(sent);
        ChunkedBinaryExtraction extr = toExtr(sent, xs,xl, rs,rl, ys,yl);
        extr.setProperty("docId", docId);
        extr.setProperty("conf", Double.toString(conf));
        extractions.add(extr);
View Full Code Here
92
93
94
95
96
97
98
        return Arrays.asList(s.split(" "));
    }
   
    private static ChunkedSentence toSent(String toks, String pos,
            String chunks) throws Exception {
        return new ChunkedSentence(split(toks), split(pos), split(chunks));
    }
View Full Code Here
332
333
334
335
336
337
338
339
340
341
342
343
        if (fields.size() < 1) {
            throw new IllegalArgumentException("must have at least 1 field");
        }

        for (int i = 0; i < fields.size(); i++) {
            ChunkedSentence sent1 = fields.get(i).getSentence();
            ChunkedSentence sent2 = fields.get((i + 1) % fields.size())
                    .getSentence();
            if (!sent1.equals(sent2)) {
                throw new IllegalArgumentException(
                        "fields must come from the same sentence");
            }
View Full Code Here
TOP

Related Classes of edu.washington.cs.knowitall.nlp.ChunkedSentence

  • edu.washington.cs.knowitall.argumentidentifier.ArgLearnerFeatureSet
  • edu.washington.cs.knowitall.examples.ReVerbExample
  • edu.washington.cs.knowitall.extractor.ChunkedArgumentExtractor
  • edu.washington.cs.knowitall.extractor.conf.featureset.ExtractionFeature
  • edu.washington.cs.knowitall.extractor.conf.HypotheticalFeatures
  • edu.washington.cs.knowitall.extractor.conf.LabeledBinaryExtractionReader$LBEIterator
  • edu.washington.cs.knowitall.extractor.conf.LabeledBinaryExtractionWriter
  • edu.washington.cs.knowitall.extractor.conf.NestedFeatures
  • edu.washington.cs.knowitall.extractor.conf.ReVerbFeatures
  • edu.washington.cs.knowitall.extractor.mapper.ConjunctionCommaArgumentFilter
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.