Team | submissionID | F2 | Prec | Recall | MAP | R_5 | R_10 | R_30 |
---|---|---|---|---|---|---|---|---|
CAPTAIN | CAPTAIN.allEnssMissq | 0.7645 | 0.7333 | 0.8000 | 0.6988 | 0.7656 | 0.8516 | 0.8906 |
CAPTAIN | CAPTAIN.allEnssBoostraping | 0.7545 | 0.7233 | 0.7900 | 0.6988 | 0.7656 | 0.8516 | 0.8906 |
JNLP | JNLP3 | 0.7526 | 0.6517 | 0.8300 | 0.7166 | 0.8125 | 0.8516 | 0.9062 |
CAPTAIN | CAPTAIN.bjpAll | 0.7489 | 0.7133 | 0.7850 | 0.8539 | 0.8906 | 0.9141 | 0.9609 |
NOWJ | NOWJ.ensemble | 0.7345 | 0.6892 | 0.7750 | 0.7975 | 0.7969 | 0.8203 | 0.8984 |
HUKB | HUKB1 | 0.6793 | 0.6342 | 0.7150 | 0.7463 | 0.7656 | 0.8438 | 0.9375 |
JNLP | JNLP2 | 0.6694 | 0.6487 | 0.7100 | 0.6926 | 0.7422 | 0.8047 | 0.8906 |
HUKB | HUKB3 | 0.6691 | 0.6567 | 0.6900 | 0.7480 | 0.7578 | 0.8516 | 0.9375 |
JNLP | JNLP1 | 0.6637 | 0.6717 | 0.6850 | 0.6930 | 0.7422 | 0.8047 | 0.8906 |
LLNTU | LLNTUgigo | 0.6600 | 0.7400 | 0.6500 | 0.7716 | 0.8125 | 0.8984 | 0.9297 |
HUKB | HUKB2 | 0.6549 | 0.6850 | 0.6650 | 0.7480 | 0.7578 | 0.8516 | 0.9375 |
LLNTU | LLNTUtdidf | 0.6389 | 0.7100 | 0.6300 | 0.7698 | 0.8359 | 0.8828 | 0.9375 |
UA | UA.TFIDF_threshold2 | 0.5698 | 0.6267 | 0.5700 | 0.6612 | 0.6797 | 0.8047 | 0.8516 |
UA | UA.TFIDF_threshold1 | 0.5600 | 0.6400 | 0.5500 | 0.6612 | 0.6797 | 0.8047 | 0.8516 |
UA | UA.BM25 | 0.5556 | 0.6400 | 0.5450 | 0.6547 | 0.6797 | 0.8047 | 0.8750 |
LLNTU | LLNTUkiwiord | 0.3856 | 0.4300 | 0.3800 | 0.5153 | 0.6016 | 0.6953 | 0.8359 |
This formal run results table is updated from the ICAIL 2023 proceedings, whose results were formerly notified to the participants, by excluding one of the questions. After finalizing the overview paper, we found that question for R04-04-E in English is not an appropriate translation of the original Japanese question. That question has been excluded of the overall evaluation, which was then performed on the remaining 100 questions.