Package edu.stanford.nlp.ling

Examples of edu.stanford.nlp.ling.Word

66
67
68
69
70
71
72
73
74
75
76
        ArrayList<Word> Words = StringToWordsTokenizer.tokenize(text);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        opts.setParseRelations(true);
        ParsedData resultData = sParser.parse(Words, opts);
        Word featureWord = new Word(feature);
        int featIndex = Words.indexOf(featureWord);
        Sentiment sentimentResult = Sentiment.Neutral;
        if (!feature.equals("") && featIndex != -1) {
            WordPos theFeature = resultData.getWordByIndex(featIndex);
            return classifyTextByFeatures(resultData, Words, theFeature);
View Full Code Here
221
222
223
224
225
226
227
228
229
230
231
    private double computeWordWeight(WordPos currentWord, ArrayList<Word> allWords) {
        String wordString = allWords.get(currentWord.getWordIndex()).word();
        int sign = wordString.contains("N##") ? -1 : 1;
        if (sign == -1) {
            allWords.set(currentWord.getWordIndex(), new Word(wordString.replace("N##", "")));
        }
        Double wordWeight = aggregator.getWordScore(currentWord, allWords);
        if (wordWeight != null && wordWeight == 0 & sign == -1) {
            return -0.5;
        }
View Full Code Here
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
        return sign * wordWeight;
    }

    private void tagNegation(ArrayList<Word> allWords) {
        boolean negationFound = false;
        Word currentWord;
        List<Word> tempPattern;
        boolean exceptionFound;
        for (int i = 0; i < allWords.size(); i++) {
            currentWord = allWords.get(i);
            if (clauseEnds.contains(currentWord.toString())) {
                // Reset as a there is a new clause
                negationFound = false;
                continue;
            }
            if (negationWords.contains(currentWord.toString())) {
                // check if this is one of the exceptions
                exceptionFound = false;
                for (ArrayList<Word> exceptionPattern : negationExceptions) {
                    tempPattern = allWords.subList(i, i + (exceptionPattern.size()));
                    if (tempPattern.containsAll(exceptionPattern)) {
                        exceptionFound = true;
                    }
                }
                if (!exceptionFound) {
                    negationFound = !negationFound;
                }
            } else {
                if (negationFound) {
                    currentWord.setWord("N##" + currentWord.word());
                }
            }
        }
    }
View Full Code Here
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
        String[] tokens;
        for (String exception : exs) {
            tokens = exception.split(" ");
            currentEx = new ArrayList<Word>();
            for (String token : tokens) {
                currentEx.add(new Word(token));
            }
            negationExceptions.add(currentEx);
        }
        ArrayList<String> inverters = FilesReader.getAllLines(PropertiesGetter.getProperty("InvertersFile"));
        parsedInverters = new ArrayList<ArrayList<Word>>();
        ArrayList<Word> currentInverter;
        String[] lineTokens;
        for (String inverter : inverters) {
            currentInverter = new ArrayList<Word>();
            lineTokens = inverter.split(" ");
            for (String token : lineTokens) {
                currentInverter.add(new Word(token));
            }
            parsedInverters.add(currentInverter);
        }

    }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
    } else {
      // Showing tokenization and parsing in code a couple of different ways.
      String[] sent = { "This", "is", "an", "easy", "sentence", "." };
      List<HasWord> sentence = new ArrayList<HasWord>();
      for (String word : sent) {
        sentence.add(new Word(word));
      }

      String sent2 = ("This is a slightly longer and more complex " +
                      "sentence requiring tokenization.");
      // Use the default tokenizer for this TreebankLanguagePack
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
    List<CoreLabel> words = new ArrayList<CoreLabel>();
    String[] testWords = {"I", "think", "I", "'ll",
                          "go", "to", "Boston", "."};

    for (String word : testWords) {
      CoreLabel label = new CoreLabel(new Word(word));
      label.setWord(label.value());
      words.add(label);
    }

    tagger.tagCoreLabels(words);
View Full Code Here
872
873
874
875
876
877
878
879
880
881
882
    // GrammaticalStructure.

    List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
    List<TypedDependency> dependencies = new ArrayList<>();

    IndexedWord root = new IndexedWord(new Word("ROOT"));
    root.set(CoreAnnotations.IndexAnnotation.class, 0);

    for (int i = 1; i <= result.n; i++) {
      int head = result.getHead(i);
      String label = result.getLabel(i);
View Full Code Here
342
343
344
345
346
347
348
349
350
351
352
353
          if (parse) {
            tree.pennPrint(pw);
          } else {
            Iterator sentIter = s.iterator();
            for (; ;) {
              Word word = (Word) sentIter.next();
              pw.print(word.word());
              if (sentIter.hasNext()) {
                pw.print(" ");
              } else {
                break;
              }
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
          }
        } else if (word instanceof HasTag) {
          TaggedWord tw = new TaggedWord(word.word(), ((HasTag) word).tag());
          sentenceB.add(tw);
        } else {
          sentenceB.add(new Word(word.word()));
        }
      }
      for (HasWord word : sentenceB) {
        word.setWord(op.wordFunction.apply(word.word()));
      }
View Full Code Here
689
690
691
692
693
694
695
696
697
    if (op.testOptions.verbose) {
      System.err.println("Adding missing final punctuation to sentence.");
    }
    String[] sfpWords = tlp.sentenceFinalPunctuationWords();
    if (sfpWords.length > 0) {
      sentence.add(new Word(sfpWords[0]));
    }
    return true;
  }
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.ling.Word

  • edu.stanford.nlp.ie.machinereading.domains.ace.reader.RobustTokenizer
  • edu.stanford.nlp.ie.machinereading.structure.ExtractionSentence
  • edu.stanford.nlp.ie.pascal.ISODateInstance
  • edu.stanford.nlp.parser.lexparser.ChineseCharacterBasedLexiconTraining
  • edu.stanford.nlp.parser.lexparser.demo.ParserDemo2
  • edu.stanford.nlp.parser.lexparser.ExhaustiveDependencyParser
  • edu.stanford.nlp.parser.lexparser.FactoredParser
  • edu.stanford.nlp.parser.lexparser.LexicalizedParser
  • edu.stanford.nlp.parser.lexparser.LexicalizedParserQuery
  • edu.stanford.nlp.parser.lexparser.MaxMatchSegmenter
    • 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.