Topic tracking for radio, TV broadcast, and newswire

We present our tracking system for the 1998 Topic Detection and Tracking project (TDT-2). This project addresses multiple sources of information in the form of both text and speech from newswire, radio and television news broadcast programs. Our tracking system is probability based and we successfully solve the problem of score normalization across topics with a simple but e ective solution. Tested on the 20K TDT-2 stories collected between March and April 1998, our tracking system achieves a performance of 1.5% miss error (on closed caption and newswire) and 3.0% miss error (on automatic speech recognition output and newswire) at the cost of 0.1% false alarm error. In the 1998 TDT-2 evaluation, our tracking system was ranked the best with the o cial topic-weighted Ctrack measure of 0.0056. We observed that there was no degradation in tracking performance due to the speech recognition errors.