The document collection used in the TREC-8 QA task was the set of documents on TREC disks 4&5 minus the Congressional Record documents.

The questions were mostly contributed by participants or developed by NIST assessors. A few questions were mined from the FAQFinder system's logs. The test set consisted of 200 questions. Two questions, questions 131 and 184, were not used when computing final scores because it was determined during judging that the document collection did not contain an answer to those questions.

TREC-8 development set of questions with answers.
This set of questions was distributed to participants so they could train their systems.

The format for each question is a question number, the text of the question, and then one or more answer strings followed by the id of a document that supports the answer.

TREC-8 test questions

TREC-8 top docs ranked list

TREC-8 judgment set (.gz)

TREC-8 pattern set

TREC-8 pattern evaluation perl script

TREC-8 original answers

The TREC-8 questions were developed expressly for the track. This file lists the answers submitted along with the question by the question creator.