Examples of joshua.prefix_tree.ExtractRules

joshua.prefix_tree.ExtractRules
Main program to extract hierarchical phrase-based statistical translation rules from an aligned parallel corpus using the suffix array techniques of Lopez (2008). @author Lane Schwartz @version $LastChangedDate:2008-11-13 13:13:31 -0600 (Thu, 13 Nov 2008) $ @see "Lopez (2008)"

      compileJoshDir.setTargetCorpus(targetCorpusFileName);
      compileJoshDir.setAlignments(alignmentFileName);
      compileJoshDir.setOutputDir(joshDirName);
      compileJoshDir.execute();
      
      ExtractRules extractRules = new ExtractRules();
      extractRules.setJoshDir(joshDirName);
      extractRules.setTestFile(testFileName);
      extractRules.setOutputFile(rulesFileName);
      extractRules.execute();
      
    } catch (IOException e) {
      Assert.fail("Unable to write temporary file. " + e.toString());
    } catch (ClassNotFoundException e) {
      Assert.fail("Unable to extract rules. " + e.toString());

View Full Code Here

    compileJoshDir.setTargetCorpus(targetFileName);
    compileJoshDir.setAlignments(alignmentFileName);
    compileJoshDir.setOutputDir(joshDirName);
    compileJoshDir.execute();
    
    ExtractRules extractRules = new ExtractRules();
    extractRules.setSentenceInitialX(sentenceInitialX);
    extractRules.setSentenceFinalX(sentenceFinalX);
    extractRules.setEdgeXViolates(violatingX);
    extractRules.setMaxPhraseLength(5);
    extractRules.setMinNonterminalSpan(minNonterminalSpan);
    extractRules.setJoshDir(joshDirName);
    extractRules.setTestFile(testFileName);
    extractRules.setOutputFile(rulesFileName);
    try {
      extractRules.execute();
    } catch (ClassNotFoundException e) {
      e.printStackTrace();
      Assert.fail(e.getLocalizedMessage());
    }

View Full Code Here

TOP

Related Classes of joshua.prefix_tree.ExtractRules

joshua.corpus.alignment.AlignmentGrids

joshua.corpus.alignment.Alignments

joshua.corpus.alignment.mm.MemoryMappedAlignmentGrids

joshua.corpus.Corpus

joshua.corpus.mm.MemoryMappedCorpusArray

joshua.corpus.suffix_array.FrequentPhrases

joshua.corpus.suffix_array.mm.MemoryMappedSuffixArray

joshua.corpus.suffix_array.ParallelCorpusGrammarFactory

joshua.corpus.suffix_array.Suffixes

joshua.corpus.vocab.SymbolTable

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.