NTCIR Workshop 9 GeoTime Task Formal Run Evaluation Results

[NTCIR Home]

Evaluation Results

• Evaluation results for English document search (from English or Japanese topics, i.e. E=>E, J=>E)
  • Results (average precision (AP), Q-measure, nDCG values) for individual runs [AVERAGE_MEASURES_ALL_RUNS_EN.xlsx]
  • Evaluation results for individual topics [AVERAGE_PERTOPIC_MEASURES_EN.xls],
  • Individual Runs and Maximum/Median/Minimum AP performance per topic [topic_matrix_AP_EN.xls]
  • Evaluation results for each participating group [BRKLY_EN.zip,GETUA_EN.zip, INESCID_EN.zip, IRNLP_EN.zip, OKSAT_EN.zip, RMIT_EN.zip, SINAIUJAEN_EN.zip, SJTUBCMI_EN.zip, UIOWA_EN.zip]
• Evaluation results for Japanese document search (from Japanese or English topics, i.e. J=>J, E=>J
  • Results (average precision, Q-measure, nDCG values)for individual runs [AVERAGE_MEASURES_ALL_RUNS_JA.xlsx]
  • Evaluation results for individual topics [AVERAGE_PERTOPIC_MEASURES_JA.xls]
  • Individual runs and Maximum/Median/Minimum performance per topic [topic_matrix_AP_JA.xls]
  • Evaluation results for official participating groups [BRKLY_JA.zip, HUKB_JA.zip, KOLIS_JA.zip, NAK_JA.zip, OKSAT_JA.zip, RMIT_JA.zip]

 

These results were used in the overview paper:

Gey, F., Larson, R., Machado, J., Yoshioka, M. (2011) NTCIR9-GeoTime Overview - Evaluating Geographic and Temporal Search: Round 2. In Proceedings of the 9^th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, Tokyo, December 6-9, 2011.