| N04-1040 | research groups have developed story | link detection systems | . The best current technology |
| P03-1030 | In the extreme case , a perfect | link detection system | performs perfectly on the NED |
| N04-1040 | documents are linked , state-ofthe-art | link detection systems | perform three primary processing |
| P03-1030 | and link detection ( LNK ) . A | link detection system | detects whether two stories are |
| N04-1040 | measures . As in the basic story | link detection system | , a similarity score between |
| P03-1030 | on the performance of a story | link detection system | and a new event detection system |
| N04-1040 | system was the best performing | Link Detection system | at TDT2002 . We can not compare |
| N04-1040 | Abstract State-of-the-art story | link detection systems | , that is , systems that determine |
| N03-3001 | The evaluation methodology of a | link detection system | requires the system to output |
| N04-1040 | require frequent retraining of a | link detection system | since new stories often discuss |
| N04-1040 | investigations in improving the basic story | link detection systems | by using source specific information |
| N04-1040 | improving the performance of a | link detection system | by using a variety of similarity |
| P03-1030 | the TDT-2002 evaluation , our | Link Detection system | was the best of three systems |
| N04-1040 | results with the other TDT2002 | Link Detection systems | because participants in TDT agree |
| N04-1040 | and was used by all the TDT 2002 | link detection systems | ( unpub - lished presentations |
| N04-1040 | system was the bestperforming | link detection system | at TDT-2002 . 2 Background and |
| N04-1040 | In contrast to the basic story | link detection system | , a variety of similarity measures |
| N04-1040 | performance over single similarity | link detection systems | ; the difference between the |
