Uploaded image for project: 'Mahout'
  1. Mahout
  2. MAHOUT-242

LLR Collocation Identifier

    XMLWordPrintableJSON

Details

    • New Feature
    • Status: Closed
    • Minor
    • Resolution: Fixed
    • 0.3
    • 0.3
    • None
    • None

    Description

      Identifies interesting Collocations in text using ngrams scored via the LogLikelihoodRatio calculation.

      As discussed in:

      Current form is a tar of a maven project that depends on mahout. Build as usual with 'mvn clean install', can be executed using:

      mvn -e exec:java  -Dexec.mainClass="org.apache.mahout.colloc.CollocDriver" -Dexec.args="--input src/test/resources/article --colloc target/colloc --output target/output -w"
      

      Output will be placed in target/output and can be viewed nicely using:

      sort -rn -k1 target/output/part-00000
      

      Includes rudimentary unit tests. Please review and comment. Needs more work to get this into patch state and integrate with Robin's document vectorizer work in MAHOUT-237

      Some basic TODO/FIXME's include:

      • use mahout math's ObjectInt map implementation when available
      • make the analyzer configurable
      • better input validation + negative unit tests.
      • more flexible ways to generate units of analysis (n-1)grams.

      Attachments

        1. mahout-colloc.tar.gz
          12 kB
          Drew Farris
        2. mahout-colloc.tar.gz
          14 kB
          Drew Farris
        3. MAHOUT-242.patch
          51 kB
          Drew Farris
        4. MAHOUT-242.patch
          52 kB
          Drew Farris
        5. MAHOUT-242.patch
          49 kB
          Drew Farris
        6. MAHOUT-242.patch
          52 kB
          Drew Farris
        7. MAHOUT-242.patch
          52 kB
          Drew Farris

        Activity

          People

            drew.farris Drew Farris
            drew.farris Drew Farris
            Votes:
            0 Vote for this issue
            Watchers:
            0 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: