Information for TAC 2010 Track Participants

TAC 2010 has three tracks:

• Knowledge Base Population (KBP)
  Track Coordinators: Heng Ji ([email protected]) and Ralph Grishman ([email protected])
  Web page: http://nlp.cs.qc.cuny.edu/kbp/2010/ (archived here)
  Mailing list: [email protected]
  
• Recognizing Textual Entailment (RTE)
  Track Coordinators: Danilo Giampiccolo ([email protected]) and Luisa Bentivogli ([email protected])
  Web page: http://tac.nist.gov/2010/RTE/
  Mailing list: [email protected]
  
• Summarization
  Track Coordinators: Karolina Owczarzak ([email protected]) and Hoa Trang Dang ([email protected])
  Web page: http://tac.nist.gov/2010/Summarization/
  Mailing list: [email protected]
  

The exact definitions of the tasks to be performed in each track are formulated and discussed on the track mailing list. Registering to participate in a TAC track does not automatically add you to the track's mailing list; if you are not already on the mailing list, you must subscribe yourself by following the instructions for contacting that mailing list as given in the track web page. If you were previously subscribed to the mailing list, you do not have to re-subscribe; track mailing lists are for anyone interested in the track, rather than specifically for TAC participants, and thus carry over from year to year. For questions about the track, send mail to the track coordinator (or post the question to the track mailing list once you join).

Track participants must abide by the Policies and Guidelines for Track Participants. All results submitted to TAC are archived on the TAC web site and all evaluations are published in the conference proceedings. Dissemination of TAC work and results other than in the conference proceedings is welcomed, but the conditions of participation specifically preclude any advertising claims based on TAC results.

Data and User Agreements

Data that are required for the TAC 2010 tracks are distributed at no cost to track participants. Whenever possible, data are distributed by NIST or the Linguistic Data Consortium via Web download; data are mailed as physical disks only if they cannot be made available for download. Each track home page will specify instructions for obtaining data for that track, including the user agreement forms required for accessing the data. Access to TAC 2010 data is restricted to registered TAC 2010 participants who have submitted all the required User Agreement forms.

Most data that is distributed by NIST is kept in password-protected areas of the TAC 2010 web site. Password-protected areas include the current year's test data and evaluation results. Each password-protected area of the web site will indicate which signed User Agreements are required for access. Each participating team will provide a Team ID and will receive a Team Password upon registration. Once the required User Agreement forms have been received for that team, NIST will activate the Team ID and Password to give access to the corresponding password-protected web pages on the TAC 2010 web site. Teams that have participated in past TAC cycles must register and obtain a new password for 2010. Teams must also submit new (current) User Agreement forms for 2010.

TAC 2010 track participants should follow the instructions given in the User Agreements page for submitting the "Agreement Concerning Dissemination of TAC Results" and any additional User Agreements that must be submitted to NIST for the particular tracks of interest. When submitting forms, in addition to the information requested in the User Agreements page, please include the email address of the main TAC 2010 contact person for the team, and a comment saying that the form is from a TAC 2010 registered participant. NIST needs a signed physical copy of the agreements before the team can be given any data.

Past Data

Much of the past data from TREC, DUC and TAC are available from NIST and may be useful for system development for some of the TAC tracks.

Schedule

BACK to General Information about Tracks