TREC Enterprise Track

Goal

The Enterprise Track at TREC has as primary goal to build a test collection for Enterprise Search. Enterprise search considers a user who searches the data of an organisation in order to complete some task. Enterprise search is interesting because it has not been sufficiently addressed in research, and it is of immense practical importance in real organisations.

Realisation of this track involves:

New data

Organisations often have a mixture of data types: web pages, news/email archives and document archives (for example on a shared fileserver or in a version control system). Each data type has particular characteristics, including inter and intra document structure.

New tasks

Experiments should be representative of what enterprise users search for on enterprise data. This might involve a single data type (the find a known item in email task) or integrate search across types (the adhoc search across mixed data types task).

We have already built and made available the data to construct an enterprise test collection, the W3C corpus. We have also started to develop ideas for search tasks, and invited Web Track participants to download the data and think about what tasks interest them.

Practical Information

• For participation, respond to the TREC CFP and follow instructions in the TREC welcome message;
• Mailing list: trec-ent@nist.gov (archived).
  To subscribe, send email to listproc@nist.gov with 'subscribe trec-ent' in the body.
• Wiki site (email arjen at acm dot org to obtain an account, using subject [trec-ent] Wiki account request).
• Information about the W3C corpus.