[TR-304] Make appropriate fat and learning to rank techniques within the open source release Created: 15/Apr/14  Updated: 16/Jun/14  Resolved: 03/Jun/14

Status: Resolved
Project: Terrier Core
Component/s: None
Affects Version/s: None
Fix Version/s: 4.0

Type: New Feature Priority: Major
Reporter: Craig Macdonald Assignee: Craig Macdonald
Resolution: Fixed  
Labels: None

Issue Links:
Related
is related to TR-287 Terrier assumes that all retrieved do... Resolved

 Description   
LTR stuff will be in Terrier 4.0


 Comments   
Comment by Craig Macdonald [ 20/May/14 ]

We need as follows:

From src_fat, for outputting LETOR formatted results files with multiple features:

  • o.t.applications:
    • WritableOutputFormat
  • o.t.matching:
    • FatQueryResultSet
    • FatResultSet
    • FatUtils
    • FatScoringMatching
    • FatFeaturedScoringMatching
    • TestFatCandidateResultSet
    • TestFatFullMatching
    • TestFatScoringMatching
  • o.t.m.daat:
    • FatFull
    • FatCandidateResult
    • FatCandidateResultSet

From src_optimisation:

  • in org.terrier.learning, FeaturedResultSet, FeaturedQueryResultSet, LabelDecorator, LETOROutputFormat, NormalisedLETOROutputFormat, Normalised2LETOROutputFormat

From elsewhere:

  • Jforests jar file
Comment by Craig Macdonald [ 03/Jun/14 ]

Committed r3883-r3892

Generated at Wed Dec 13 08:53:12 GMT 2017 using JIRA 7.1.1#71004-sha1:d6b2c0d9b7051e9fb5e4eb8ce177ca56d91d7bd8.