On-line new event detection and tracking
Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
Summarizing text documents: sentence selection and evaluation metrics
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Extracting significant time varying features from text
Proceedings of the eighth international conference on Information and knowledge management
Automatic generation of overview timelines
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Temporal summaries of new topics
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Detecting events with date and place information in unstructured text
Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries
Detecting and Browsing Events in Unstructured text
SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Introduction to topic detection and tracking
Topic detection and tracking
Monitoring the news: a TDT demonstration system
HLT '01 Proceedings of the first international conference on Human language technology research
An empirical study of information synthesis tasks
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Hi-index | 0.00 |
In recent years, a lot of work has been done in the field of Topic Tracking. The focus of this work has been on identifying stories belonging to the same topic. This might result in a very large number of stories being reported to the user. It might be more useful to a user if a summary of the main events in the topic rather than the entire collection of stories related to the topic were presented. Though work on such a fine-grained level has been started, there is currently no standard evaluation testbed available to measure the accuracy of such techniques. We describe a scheme for developing a testbed of user judgments which can be used to evaluate the above mentioned techniques. The corpus that we have created can also be used to evaluate single or multi-document summaries.