Uploaded image for project: 'Terrier Core'
  1. Terrier Core
  2. TR-68

Implement Multinomial Field-based DFR Model

          Details

          • Type: New Feature
          • Status: Resolved
          • Priority: Minor
          • Resolution: Fixed
          • Affects Version/s: 3.0
          • Fix Version/s: 3.0
          • Component/s: .matching
          • Labels:
            None

            Description

            See Vassilis' ECIR 2007 paper

              Attachments

                Activity

                Ascending order - Click to sort in descending order
                Hide
                Permalink
                craigm Craig Macdonald added a comment -

                Paper is at http://ir.dcs.gla.ac.uk/terrier/publications/fulltext_plachouras.pdf

                Vassilis discussed two approximations of the multinomial model, which were called ML2 and ML_

                {D}

                2. The latter of these used Lancos approximation instead of using Stirling series to calcualte the factorials in ML2.

                Show
                craigm Craig Macdonald added a comment - Paper is at http://ir.dcs.gla.ac.uk/terrier/publications/fulltext_plachouras.pdf Vassilis discussed two approximations of the multinomial model, which were called ML2 and ML_ {D} 2. The latter of these used Lancos approximation instead of using Stirling series to calcualte the factorials in ML2.
                Hide
                Permalink
                craigm Craig Macdonald added a comment -

                Ok. I have recoded to work in new version of fields. These will be committed to core in TREC-160.

                Show
                craigm Craig Macdonald added a comment - Ok. I have recoded to work in new version of fields. These will be committed to core in TREC-160 .

                  People

                  • Assignee:
                    craigm Craig Macdonald
                    Reporter:
                    craigm Craig Macdonald
                  • Watchers:
                    0 Start watching this issue

                    Dates

                    • Created:
                      Updated:
                      Resolved: