Test collections

On this page are a list of publically available IR test collections. Some are held locally and some are pointers to remote sites.

Collections held at Glasgow

               DOCS   QRYS   SIZE*

  LISA        5,872     35    3.4
  NPL        11,429     93    3.1
  CACM        3,204     64    2.2
  CISI        1,460    112    2.2
  Cranfield   1,400    225    1.6
  Time          423     83    1.5
  Medline     1,033     30    1.1
  ADI            82     35    0.04

Remote collections

• OHSUMED
  To quote from the readme file
  This test collection was created to assist information retrieval research. It is a clinically-oriented MEDLINE subset, consisting of 348,566 references (out of a total of over 7 million), covering all references from 270 medical journals over a five-year period (1987-1991).

• Reuters 21,578 collection
  The Reuters-21578 text categorization test collection is available through this link.

• TREC
  The TREC collections aren't in the public domain. However, we are now the official distributors for the following TREC collections: WT2G, WT10G, DOTGOV, DOTGOV2.
     See http://ir.dcs.gla.ac.uk/test_collections/

• Europarl Parallel Corpus
  Europarl is a parallel corpus for statistical machine translation testing.