Uploaded image for project: 'Joshua (Retired)'
  1. Joshua (Retired)
  2. JOSHUA-169

LanguageModelFF should compute partial n-grams

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Reopened
    • Resolution: Unresolved
    • None
    • 6.2
    • None
    • None

    Description

      Incomplete n-grams have no estimate, which creates a problem when comparing small phrases (early in decoding) and for short sentences. To fix this, the LanguageModelFF should compute partial n-gram scores, caching the result and the n-gram length in the DP state so that it can be subtracted off later.

      Another advantage of this is that it would likely allow a large simplification of the FeatureFunction interface, since we would no longer need a computeFinal distinction

      Attachments

        Activity

          People

            Unassigned Unassigned
            post Matt Post
            Votes:
            1 Vote for this issue
            Watchers:
            1 Start watching this issue

            Dates

              Created:
              Updated: