Examples of PairOfStrings

edu.umd.cloud9.io.pair.PairOfStrings
WritableComparable representing a pair of Strings. The elements in the pair are referred to as the left and right elements. The natural sort order is: first by the left element, and then by the right element. @author Jimmy Lin

Examples of edu.umd.cloud9.io.pair.PairOfStrings

        if (!key.getLeftElement().equals(targetTitle)) {
          return;
        }


        while (values.hasNext()) {
          PairOfStrings pair = values.next();
          SRCID.set(Integer.parseInt(pair.getLeftElement()));
          TARGET_ANCHOR_PAIR.set(targetDocid, pair.getRightElement());


          output.collect(SRCID, TARGET_ANCHOR_PAIR);
        }
      }
    }

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings


    List<PairOfWritables<PairOfStrings, FloatWritable>> list1 = Lists.newArrayList();
    List<PairOfWritables<PairOfStrings, FloatWritable>> list2 = Lists.newArrayList();


    for (PairOfWritables<PairOfStrings, FloatWritable> p : pairs) {
      PairOfStrings bigram = p.getLeftElement();


      if (bigram.getLeftElement().equals("light")) {
        list1.add(p);
      }
      if (bigram.getLeftElement().equals("contain")) {
        list2.add(p);
      }
    }


    Collections.sort(list1, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() {
      public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1,
          PairOfWritables<PairOfStrings, FloatWritable> e2) {
        if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
          return e1.getLeftElement().compareTo(e2.getLeftElement());
        }


        return e2.getRightElement().compareTo(e1.getRightElement());
      }
    });


    Iterator<PairOfWritables<PairOfStrings, FloatWritable>> iter1 =
        Iterators.limit(list1.iterator(), 10);
    while (iter1.hasNext()) {
      PairOfWritables<PairOfStrings, FloatWritable> p = iter1.next();
      PairOfStrings bigram = p.getLeftElement();
      System.out.println(bigram + "\t" + p.getRightElement());
    }


    Collections.sort(list2, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() {
      public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1,
          PairOfWritables<PairOfStrings, FloatWritable> e2) {
        if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
          return e1.getLeftElement().compareTo(e2.getLeftElement());
        }


        return e2.getRightElement().compareTo(e1.getRightElement());
      }
    });


    Iterator<PairOfWritables<PairOfStrings, FloatWritable>> iter2 =
        Iterators.limit(list2.iterator(), 10);
    while (iter2.hasNext()) {
      PairOfWritables<PairOfStrings, FloatWritable> p = iter2.next();
      PairOfStrings bigram = p.getLeftElement();
      System.out.println(bigram + "\t" + p.getRightElement());
    }
  }

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

    IntegrationUtils.exec(Joiner.on(" ").join(args));


    SequenceFile.Reader reader = new SequenceFile.Reader(conf,
        SequenceFile.Reader.file(new Path(tmpPrefix + "-base/part-r-00000")));


    PairOfStrings pair = new PairOfStrings();
    FloatWritable f = new FloatWritable();


    reader.next(pair, f);
    assertEquals("&c", pair.getLeftElement());
    assertEquals("*", pair.getRightElement());
    assertEquals(17f, f.get(), 10e-6);


    for (int i = 0; i < 100; i++) {
      reader.next(pair, f);
    }


    assertEquals("'dear", pair.getLeftElement());
    assertEquals("*", pair.getRightElement());
    assertEquals(2f, f.get(), 10e-6);


    reader.next(pair, f);
    assertEquals("'dear", pair.getLeftElement());
    assertEquals("lord", pair.getRightElement());
    assertEquals(1f, f.get(), 10e-6);


    reader.close();
  }

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);


      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);


      if (probEF > 0 && e > 0 && !docLangTokenizer.isStopWord(eTerm) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {      
        // assuming our bilingual dictionary is learned from normally segmented text, but we want to use bigram tokenizer for CLIR purposes
        // then we need to convert the translations of each source token into a sequence of bigrams
        // we can distribute the translation probability equally to the each bigram
        if (bigramSegment) {
          String[] eTokens = docLangTokenizer.processContent(eTerm);

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

        String[] parts = rule.split("\\|\\|\\|");
        String[] lhs = parts[1].trim().split(" ");
        String[] rhs = parts[2].trim().split(" ");;
        for (String l : lhs) {
          for (String r : rhs) {
            pairsInSCFG.add(new PairOfStrings(l, r));
          }
        }
      }
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

        String[] parts = rule.split("\\|\\|\\|");
        String[] lhs = parts[0].trim().split(" ");
        String[] rhs = parts[1].trim().split(" ");;
        for (String l : lhs) {
          for (String r : rhs) {
            pairsInSCFG.add(new PairOfStrings(l, r));
          }
        }
      }
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);


      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);


      if (probEF > 0 && e > 0 && !docLangTokenizer.isStopWord(eTerm) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {      
        // assuming our bilingual dictionary is learned from normally segmented text, but we want to use bigram tokenizer for CLIR purposes
        // then we need to convert the translations of each source token into a sequence of bigrams
        // we can distribute the translation probability equally to the each bigram
        if (bigramSegment) {
          String[] eTokens = docLangTokenizer.processContent(eTerm);

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);


      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);


      if (probEF > 0 && e > 0 && !docLangTokenizer.isStemmedStopWord(eTerm) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {      
        // assuming our bilingual dictionary is learned from normally segmented text, but we want to use bigram tokenizer for CLIR purposes
        // then we need to convert the translations of each source token into a sequence of bigrams
        // we can distribute the translation probability equally to the each bigram
        if (bigramSegment) {
          String[] eTokens = docLangTokenizer.processContent(eTerm);

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

        String[] parts = rule.split("\\|\\|\\|");
        String[] lhs = parts[1].trim().split(" ");
        String[] rhs = parts[2].trim().split(" ");;
        for (String l : lhs) {
          for (String r : rhs) {
            pairsInSCFG.add(new PairOfStrings(l, r));
            //            LOG.info("added "+l+"|||"+r);
          }
        }
      }
    } catch (UnsupportedEncodingException e) {

View Full Code Here

Examples of edu.umd.cloud9.io.pair.PairOfStrings

      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);


      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);


      if (probEF > 0 && e > 0 && !docLangTokenizer.isStemmedStopWord(eTerm) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {      
        // assuming our bilingual dictionary is learned from normally segmented text, but we want to use bigram tokenizer for CLIR purposes
        // then we need to convert the translations of each source token into a sequence of bigrams
        // we can distribute the translation probability equally to the each bigram
        if (bigramSegment) {
          String[] eTokens = docLangTokenizer.processContent(eTerm);

View Full Code Here

0 1 2

TOP

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.