Examples of edu.umd.cloud9.webgraph.data.AnchorText

edu.umd.cloud9.io.map.HMapSFW

This data structure represents a line of anchor text. A line of anchor text has some text, a weight, and a set of sources (targets) associated with it. Sources (targets) are the pages a line of anchor text originates from (points to) when the underlying link is an incoming (outgoing) link.

The implemented iterator makes it possible to iterate through the source or target documents for each line of anchor text.
@author Nima Asadi

    }
    return cnt;
  }


  private static HMapSFW array2Map(String[] array) {
    HMapSFW map = new HMapSFW();
    for ( int i = 0; i < array.length; i += 2 ) {
      map.put(array[i], Float.parseFloat(array[i+1]));
    }
    return map;
  }

View Full Code Here

    });
    grammar_AP.put(2, new String[] {
        "35", "0.1807","36", "0.0027","33", "0.0241","34", "0.0044","39", "0.3323","37", "0.3308","38", "0.0064","43", "0.0","42", "0.4085","41", "0.2136","40", "0.5166","67", "0.6253","66", "0.2055","69", "0.5464","68", "0.2556","26", "0.0082","27", "0.3113","28", "0.0058","29", "0.5319","30", "0.6832","32", "0.3168","31", "0.081","70", "0.5252","71", "0.219","72", "0.0278","73", "0.2601","74", "0.0302","75", "0.1449","59", "0.7421","58", "0.1165","57", "0.0905","56", "0.3992","55", "0.636","64", "6.0E-4","65", "0.5581","62", "0.0492","63", "0.0815","60", "0.7408","61", "0.0905","49", "0.7575","48", "0.7018","45", "0.3528","44", "0.1752","47", "0.3373","46", "0.3308","51", "0.0628","52", "0.0749","53", "0.0038","54", "0.0415","50", "0.7537"
    });


    HMapSFW tenbestAPMap = array2Map(Nbest_AP.get(2));
    HMapSFW onebestAPMap = array2Map(Onebest_AP.get(2));
    HMapSFW grammarAPMap = array2Map(grammar_AP.get(2));
    HMapSFW tokenAPMap = array2Map(baseline_token_AP);
    HMapSFW gridAPMap = array2Map(Interp_AP.get(2));


    System.out.println(countNumberOfImprovedTopics(tokenAPMap, gridAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, tenbestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, onebestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, grammarAPMap));

View Full Code Here

    }
    return cnt;
  }


  private static HMapSFW array2Map(String[] array) {
    HMapSFW map = new HMapSFW();
    for ( int i = 0; i < array.length; i += 2 ) {
      map.put(array[i], Float.parseFloat(array[i+1]));
    }
    return map;
  }

View Full Code Here

    return new JUnit4TestAdapter(EnFr_CLEF06.class);
  }


  public static void main(String[] args) {
    initialize();
    HMapSFW tenbestAPMap = array2Map(Nbest_AP.get(2));
    HMapSFW onebestAPMap = array2Map(Onebest_AP.get(2));
    HMapSFW grammarAPMap = array2Map(grammar_AP.get(2));
    HMapSFW tokenAPMap = array2Map(baseline_token_AP);
    HMapSFW gridAPMap = array2Map(Interp_AP.get(2));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, gridAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, tenbestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, onebestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, grammarAPMap));
    System.out.println(countNumberOfNegligibleTopics(tokenAPMap, gridAPMap));

View Full Code Here

    }
    return cnt;
  }


  private static HMapSFW array2Map(String[] array) {
    HMapSFW map = new HMapSFW();
    for ( int i = 0; i < array.length; i += 2 ) {
      map.put(array[i], Float.parseFloat(array[i+1]));
    }
    return map;
  }

View Full Code Here

    return new JUnit4TestAdapter(EnZh_NTCIR8.class);
  }


  public static void main(String[] args) {
    //    HMapSFW gridAPMap = array2Map(Interp_AP);
    HMapSFW tenbestAPMap = array2Map(Nbest_AP.get(2));
    HMapSFW onebestAPMap = array2Map(Onebest_AP.get(1));
    HMapSFW grammarAPMap = array2Map(grammar_AP.get(0));
    HMapSFW tokenAPMap = array2Map(baseline_token_AP);
    //    System.out.println(countNumberOfImprovedTopics(tokenAPMap, gridAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, tenbestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, onebestAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, grammarAPMap));
    System.out.println(countNumberOfImprovedTopics(tokenAPMap, tokenAPMap));

View Full Code Here

    }
    return cnt;
  }


  private static HMapSFW array2Map(String[] array) {
    HMapSFW map = new HMapSFW();
    for ( int i = 0; i < array.length; i += 2 ) {
      map.put(array[i], Float.parseFloat(array[i+1]));
    }
    return map;
  }

View Full Code Here

    transPhrase = transPhrase.trim();


    //LOG.info("Found translation phrase " + transPhrase);


    if (!phrase2score.containsKey(fPhrase)) {
      phrase2score.put(fPhrase, new HMapSFW());
    }
    // if same phrase extracted from multiple rules, average prob.s


    HMapKF<String> scoreTable = phrase2score.get(fPhrase);

View Full Code Here


    // scfgDist table is a set of (source_token --> X) maps, where X is a set of (token_trans --> score) maps
    Map<String,HMapSFW> scfgDist = new HashMap<String,HMapSFW>();


    // phrase2count table is a set of (source_phrase --> X) maps, where X is a set of (phrase_trans --> count) maps
    HMapSFW phraseDist = new HMapSFW();


    HMapSIW srcTokenCnt = new HMapSIW();


    Set<String> bagOfTargetTokens = new HashSet<String>();

View Full Code Here

          continue;      
        }
        bagOfTargetTokens.add(eTerm);
        if (isOne2Many <= 1) {
          if (probDist.containsKey(fTerm)) {
            HMapSFW eToken2Prob = probDist.get(fTerm);
            eToken2Prob.increment(eTerm, weight);
          }else {
            HMapSFW eToken2Prob = new HMapSFW();
            eToken2Prob.put(eTerm, weight);
            probDist.put(fTerm, eToken2Prob);
          }
        }
      }


      if (isOne2Many == 2) {
        // if ids.size() > 1 eTerm is a multi-token expression
        // even if eTerm is overwritten here, we need to do above loop to update bagOfTargetTokens
        if (ids.size() > 1) {
          eTerm = isConsecutiveWithStopwords(ids, rhs, docLangTokenizer);     // <---- heuristic
        }


        // no proper translation on target-side (e.g., stopword OR non-consecutive multi-word translation), let's skip
        if (eTerm == null) {
          continue;
        }


        eTerm = Utils.removeBorderStopWords(docLangTokenizer, eTerm);
        
        // this is difference between one-to-many and one-to-one heuristics for 1-best MT case
        // we add multi-token expressions in addition to single target tokens,
        bagOfTargetTokens.add(eTerm);


        // update prob. distr.
        if (probDist.containsKey(fTerm)) {
          HMapSFW eToken2Prob = probDist.get(fTerm);
          eToken2Prob.increment(eTerm, weight);
        }else {
          HMapSFW eToken2Prob = new HMapSFW();
          eToken2Prob.put(eTerm, weight);
          probDist.put(fTerm, eToken2Prob);
        }
      }
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of edu.umd.cloud9.webgraph.data.AnchorText

bak.pcj.IntIterator

edu.umd.cloud9.example.bfs.BfsNodeTest

edu.umd.cloud9.example.pagerank.PageRankNodeTest

edu.umd.cloud9.io.array.ArrayListOfIntsWritable

edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest

edu.umd.cloud9.io.map.HMapIDW

edu.umd.cloud9.io.map.HMapIDWTest

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.