J. Carbonell, Y. Yang, J. Lafferty, R.D. Brown, T.P., and X. Liu. Cmu report on tdt-2: Segmentation, detection and tracking. In DARPA Broadcast News Conference, 1999. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
The LIMSI Topic Tracking System for TDT2002 - Lo, Gauvain (7 citations) (Correct)
....that there is no story boundary for the ASR transcription, i.e. system needs to automatically determine the story boundaries. In the TDT2001 evaluation, the story boundaries from the IBM automatic story segmentation system were available. The automatic BN segmentation systems of IBM [5] and CMU [3] were reported in earlier TDT evaluations. The main feature of both systems is the use of models trained on specific sources to indicate story changes. For example, certain cue words on the left or right sides of stories, such as C.N.N. news often appear at the end of the C.N.N. news reports. ....
J. Carbonell, Y. Yang, J. Lafferty, R.D. Brown, T.P., and X. Liu. Cmu report on tdt-2: Segmentation, detection and tracking. In DARPA Broadcast News Conference, 1999.
Perspectives on Information Retrieval and Speech - Allan (2002) (1 citation) (Correct)
....two months worth of news from several sources, approximately 13,000 news stories. 2 The results were: For tracking, ASR errors had a modest impact on e#ectiveness, but not a substantial drop. 13] For clustering the stories into topics, the ASR errors had almost no impact on e#ectiveness. [4] When detecting the onset of a new event, ASR errors did have a substantially greater impact. 1] It is not entirely clear why ASR errors had a larger impact on the new event detection. I suspect it is because the task itself is so di#cult (e#ectiveness is generally poor) that ASR errors have ....
Jaime Carbonell, Yiming Yang, John La#erty, Ralf D. Brown a nd Tom Pierce, and Xin Liu. CMU report on TDT-2: Segmentation, detection and tracking. In Proceedings of the DARPA Broadcast News Workshop, pages 117--120. Morgan Kau#man Publishers, 1999.
Link Detection - Results and Analysis - Brown, Pierce, Yang, Carbonell (2000) Self-citation (Carbonell Yang Brown Pierce) (Correct)
....by a common code library for loading TDT story collections and processing the test data file; the only code which must be implemented for each new SLD system is the actual similarity confidence computation. This common library is an outgrowth of the DTREE topic tracker from the TDT 2 project [1, 4]. These systems were run on three distinct data sets. The first ( dry run ) consisted of story pairs selected from the six months of news stories originally collected for the TDT 2 project in 1998; the second ( evaluation ) consisted of previously unseen pairs selected from an additional three ....
Jaime Carbonell, Yiming Yang, John Lafferty, Ralf D.Brown, Tom Pierce, and Xin Liu. CMU report on TDT-2: Segmentation, Detection and Tracking. In Proceedings of the DARPA Broadcast News Workshop, pages 117--120, San Francisco, CA, 1999. Morgan Kaufmann Publishers, Inc.
A Server for Real-Time Event Tracking in News - Brown (2001) Self-citation (Brown) (Correct)
....University 5000 Forbes Avenue Pittsburgh, PA 15213 3890 USA ralf cs.cmu.edu 1. INTRODUCTION As the flood of information continues to grow, it becomes ever more necessary to extract just the portion of the flow which is of interest to each user. The Topic Detection and Tracking (TDT) project [1, 3, 6, 5] addressed and continues to address this need, but has been of necessity applied in a batch processing context on a static collection. What is required for topic detection and tracking to be of utility to end users is a real time system which operates on a live stream of information. This paper ....
J. Carbonell, Y. Yang, J. Lafferty, R. D.Brown, T. Pierce, and X. Liu. CMU report on TDT-2: Segmentation, Detection and Tracking. In Proceedings of the DARPA Broadcast News Workshop, pages 117--120, San Francisco, CA, 1999. Morgan Kaufmann Publishers, Inc.
Improving Text Categorization Methods for Event Tracking - Yang, Ault, Pierce, Lattimer (2000) (13 citations) Self-citation (Yang Pierce) (Correct)
.... (TDT) is a new line of research composed of three major sub problems: segmenting speech recognized TV radio broadcasts into news stores, detecting novel events in segmented or unsegmented news streams, and tracking the development of an event based upon human identified sample stories of that event[1, 24, 22, 3]. This last task, event tracking, is the focus of our research in this paper. The problem is defined as automatically assigning pre defined event labels to documents presented to the system in a chronological order. An event in the TDT context is something that occurs at specific place and time ....
Jaime Carbonell, Yiming Yang, John Lafferty, Ralf D.Brown, Tom Pierce, and Xin Liu. Cmu report on tdt-2: Segmentation, detection and tracking. In Proceedings of the DARPA Broadcast News Workshop, pages 117--120, San Francisco, CA, 1999. Morgan Kaufmann Publishers, Inc.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC