Title :
Probabilistic models for topic detection and tracking
Author :
Walls, F. ; Jin, Hye-Jin ; Sista, S. ; Schwartz, R.
Author_Institution :
BBN Syst. & Technol. Corp., Cambridge, MA, USA
Abstract :
We present probabilistic models for use in detecting and tracking topics in broadcast news stories. Our information retrieval (IR) models are formally explained. The topic detection and tracking (TDT) initiative is discussed. The application of probabilistic models to the topic detection and tracking tasks is developed, and enhancements are discussed. We discuss four variations of these models, and we report our preliminary test results from the current TDT corpus
Keywords :
computational linguistics; information retrieval; natural languages; broadcast news stories; enhancements; information retrieval models; probabilistic models; topic detection; topic detection and tracking; topic tracking; Broadcast technology; Broadcasting; Clustering algorithms; Information retrieval; Partitioning algorithms; Probability; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5041-3
DOI :
10.1109/ICASSP.1999.758177
