1 | tag | team | type | judged? | NDCG@10 | P@5 | RBP(p=.5) | bpref | MAP | score-report | ||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2 | mpiid5_run3 | mpiid5 | manual | JUDGED | 0.6893 | 0.8514 | 0.7547 | 0.5679 | 0.338 | report | TREC-COVID: Effectiveness of Top-scoring Round 2 Runs | |||||
3 | mpiid5_run2 | mpiid5 | manual | UNJUDGED | 0.6864 | 0.8057 | 0.7472 | 0.4943 | 0.3185 | report | ||||||
4 | SparseDenseSciBert | CMT | feedback | JUDGED | 0.6772 | 0.76 | 0.752 | 0.5096 | 0.3115 | report | Notes: | |||||
5 | mpiid5_run1 | mpiid5 | feedback | UNJUDGED | 0.6677 | 0.7771 | 0.7305 | 0.4609 | 0.2946 | report | 1. This consists of all runs that rank in the top 50 runs for at least one of the measures. | |||||
6 | UIowaS_Run3 | UIowaS | feedback | UNJUDGED | 0.6382 | 0.7657 | 0.7037 | 0.4867 | 0.2845 | report | Runs that did not make it into the top 50 for any measure may mave better | |||||
7 | UIowaS_Run1 | UIowaS | feedback | JUDGED | 0.6365 | 0.76 | 0.7042 | 0.4853 | 0.283 | report | scores for some measures than the runs at the bottom of this list for | |||||
8 | UIowaS_Run2 | UIowaS | feedback | UNJUDGED | 0.6349 | 0.7714 | 0.699 | 0.4887 | 0.2855 | report | those measures. | |||||
9 | UPrrf16lgbertd50-r2 | unique_ptr | feedback | JUDGED | 0.632 | 0.7086 | 0.7153 | 0.4414 | 0.3 | report | 2. A total of 136 runs from 51 teams was submitted, counting two baseline runs | |||||
10 | GUIR_S2_run2 | GUIR_S2 | feedback | JUDGED | 0.6286 | 0.7771 | 0.6805 | 0.4067 | 0.2531 | report | in those totals. | |||||
11 | ReInfoSelect | CMT | feedback | UNJUDGED | 0.6259 | 0.6971 | 0.667 | 0.4435 | 0.285 | report | 3. Scores are means over the 35 topics in the Round 2 test set. | |||||
12 | GUIR_S2_run1 | GUIR_S2 | automatic | UNJUDGED | 0.6251 | 0.7486 | 0.6787 | 0.4569 | 0.2842 | report | 4. Judgment sets were created by pooling over the top priority run from each team | |||||
13 | covidex.t5 | covidex | automatic | JUDGED | 0.625 | 0.7314 | 0.6634 | 0.4876 | 0.288 | report | except both baseline runs were judged. For topics 1-30 the pool depth was 7. | |||||
14 | sab20.2.dfo.metadocs | sabir | feedback | JUDGED | 0.6161 | 0.7086 | 0.6746 | 0.4704 | 0.2269 | report | For topics 31-35 (the new topics in this round) the pool depth was 15. | |||||
15 | ContrastNLGSciBert | CMT | feedback | UNJUDGED | 0.6138 | 0.7314 | 0.6933 | 0.4302 | 0.2775 | report | 5. Round 2 implemented residual collection scoring, meaning all documents appearing | |||||
16 | udel_fang_L2R | udel_fang | feedback | UNJUDGED | 0.6132 | 0.6857 | 0.6426 | 0.3904 | 0.2434 | report | in the Round 1 qrels were removed from the submitted runs and are not part of the | |||||
17 | cogir-ibm-qQ-combs | CogIR | automatic | UNJUDGED | 0.6131 | 0.7086 | 0.6456 | 0.4222 | 0.259 | report | Round 2 qrels. | |||||
18 | cogir-ibm-qQ-PolRnk | CogIR | automatic | JUDGED | 0.6104 | 0.7314 | 0.648 | 0.425 | 0.2628 | report | ||||||
19 | UPrrf16bert20-r2 | unique_ptr | feedback | UNJUDGED | 0.6099 | 0.6743 | 0.6758 | 0.4391 | 0.2958 | report | Full Round 2 archive: | |||||
20 | UPrrf16lgbert50-r2 | unique_ptr | feedback | UNJUDGED | 0.6077 | 0.6971 | 0.6507 | 0.4414 | 0.2964 | report | ||||||
21 | combined_bm25_dfr | risklick | feedback | UNJUDGED | 0.5998 | 0.7143 | 0.6773 | 0.4203 | 0.2312 | report | ||||||
22 | FullTxt_R2_Time | OHSU | manual | JUDGED | 0.5969 | 0.7029 | 0.6193 | 0.4525 | 0.268 | report | ||||||
23 | elhuyar_rRnk_cbert1 | Elhuyar_NLP_team | automatic | JUDGED | 0.5912 | 0.72 | 0.6313 | 0.4793 | 0.2941 | report | ||||||
24 | xj4wang_run3 | xj4wang | manual | UNJUDGED | 0.5907 | 0.7314 | 0.6546 | 0.4823 | 0.221 | report | ||||||
25 | elhuyar_rRnk_cbert3 | Elhuyar_NLP_team | automatic | UNJUDGED | 0.5905 | 0.7314 | 0.6227 | 0.4791 | 0.2923 | report | ||||||
26 | covidex.fuse | covidex | feedback | UNJUDGED | 0.5904 | 0.6743 | 0.6544 | 0.5345 | 0.291 | report | ||||||
27 | elhuyar_rRnk_cbert2 | Elhuyar_NLP_team | automatic | UNJUDGED | 0.59 | 0.7314 | 0.6203 | 0.4772 | 0.2851 | report | ||||||
28 | cogir-ibm-q-PolRnk | CogIR | automatic | UNJUDGED | 0.589 | 0.6971 | 0.6174 | 0.4082 | 0.238 | report | ||||||
29 | combined | risklick | feedback | JUDGED | 0.5878 | 0.6971 | 0.6743 | 0.4237 | 0.2243 | report | ||||||
30 | BBGhelani3 | BBGhelani | manual | UNJUDGED | 0.5868 | 0.7543 | 0.6376 | 0.5027 | 0.2386 | report | ||||||
31 | xj4wang_run1 | xj4wang | manual | JUDGED | 0.586 | 0.7314 | 0.6543 | 0.481 | 0.2146 | report | ||||||
32 | BBGhelani1 | BBGhelani | manual | JUDGED | 0.5846 | 0.7543 | 0.6374 | 0.5045 | 0.2412 | report | ||||||
33 | BBGhelani2 | BBGhelani | manual | UNJUDGED | 0.5846 | 0.7543 | 0.6374 | 0.502 | 0.2402 | report | ||||||
34 | Emory_IRLab_Run1 | Emory_IRLab | automatic | JUDGED | 0.5832 | 0.6971 | 0.6338 | 0.3539 | 0.2247 | report | ||||||
35 | CSIROmed_RF_RR | CSIROmed | feedback | UNJUDGED | 0.5804 | 0.68 | 0.6481 | 0.4358 | 0.2176 | report | ||||||
36 | CSIROmedNIR | CSIROmed | automatic | JUDGED | 0.578 | 0.72 | 0.6899 | 0.3755 | 0.192 | report | ||||||
37 | Emory_IRLab_Run2 | Emory_IRLab | automatic | UNJUDGED | 0.5766 | 0.68 | 0.627 | 0.3528 | 0.2211 | report | ||||||
38 | CSIROmedNIRR | CSIROmed | automatic | UNJUDGED | 0.568 | 0.7029 | 0.6737 | 0.3714 | 0.1857 | report | ||||||
39 | bm25_syn_0.8_2.6 | risklick | feedback | UNJUDGED | 0.5655 | 0.6914 | 0.6635 | 0.4054 | 0.2132 | report | ||||||
40 | udel_fang_FB | udel_fang | feedback | JUDGED | 0.5625 | 0.6686 | 0.6237 | 0.4185 | 0.2436 | report | ||||||
41 | Technion-RRF | Technion | feedback | JUDGED | 0.5566 | 0.68 | 0.6236 | 0.429 | 0.2465 | report | ||||||
42 | cu_dbmi_bm25 | columbia_university_dbmi | manual | UNJUDGED | 0.5564 | 0.6171 | 0.6355 | 0.4132 | 0.2083 | report | ||||||
43 | r2.fusion2 | anserini | automatic | JUDGED | 0.5553 | 0.68 | 0.5737 | 0.4284 | 0.2725 | report | ||||||
44 | cord19.vespa.ai-bm25 | cord19.vespa.ai | automatic | UNJUDGED | 0.5549 | 0.64 | 0.6359 | 0.3607 | 0.1914 | report | ||||||
45 | Technion-LTR | Technion | feedback | UNJUDGED | 0.5491 | 0.64 | 0.5919 | 0.4252 | 0.2497 | report | ||||||
46 | DD_prf | DY_XD | automatic | JUDGED | 0.5482 | 0.6629 | 0.6018 | 0.3802 | 0.2064 | report | ||||||
47 | sab20.2.meta.docs | sabir | automatic | UNJUDGED | 0.543 | 0.6457 | 0.5871 | 0.4211 | 0.2452 | report | ||||||
48 | cord19.vespa.ai-gbdt | cord19.vespa.ai | feedback | JUDGED | 0.5422 | 0.6686 | 0.6324 | 0.3887 | 0.1884 | report | ||||||
49 | IRIT_markers_all | IRIT_markers | automatic | JUDGED | 0.5366 | 0.6629 | 0.6089 | 0.4348 | 0.2174 | report | ||||||
50 | IRIT_markers_base_mu | IRIT_markers | automatic | UNJUDGED | 0.5292 | 0.6514 | 0.6025 | 0.4327 | 0.214 | report | ||||||
51 | IRIT_markers_base_un | IRIT_markers | automatic | UNJUDGED | 0.529 | 0.6629 | 0.6083 | 0.4343 | 0.2169 | report | ||||||
52 | Technion-JPDs | Technion | feedback | UNJUDGED | 0.5221 | 0.5943 | 0.6007 | 0.4268 | 0.2356 | report | ||||||
53 | TF_IDF_Bo1QE | UB_BW | automatic | UNJUDGED | 0.5149 | 0.6171 | 0.547 | 0.3829 | 0.2209 | report | ||||||
54 | CincyMedIR-11 | CincyMedIR | feedback | JUDGED | 0.5122 | 0.6286 | 0.6134 | 0.3544 | 0.1749 | report | ||||||
55 | ES_Defaults | CovidSearch | automatic | UNJUDGED | 0.5112 | 0.6686 | 0.5628 | 0.3991 | 0.2117 | report | ||||||
56 | FullTxt_R2_Orig | OHSU | manual | UNJUDGED | 0.5103 | 0.6114 | 0.5079 | 0.4479 | 0.2373 | report | ||||||
57 | run1 | cuni | automatic | JUDGED | 0.5092 | 0.6343 | 0.5951 | 0.3919 | 0.2037 | report | ||||||
58 | COMBSUM | UB_BW | automatic | JUDGED | 0.5028 | 0.6114 | 0.5471 | 0.3784 | 0.2135 | report | ||||||
59 | sab20.2.dfo.meta | sabir | feedback | UNJUDGED | 0.4927 | 0.5657 | 0.553 | 0.4226 | 0.1677 | report | ||||||
60 | BITEM_BL | BITEM | automatic | JUDGED | 0.4875 | 0.6 | 0.5411 | 0.4358 | 0.218 | report | ||||||
61 | r2.fusion1 | anserini | automatic | JUDGED | 0.4827 | 0.6114 | 0.5428 | 0.4003 | 0.2418 | report | ||||||
62 | irc_logreg_tfidf | IRC | feedback | UNJUDGED | 0.417 | 0.5371 | 0.4841 | 0.4025 | 0.1666 | report | ||||||
63 | xj4wang_run2 | xj4wang | manual | UNJUDGED | 0.3474 | 0.3543 | 0.2464 | 0.4862 | 0.1742 | report | ||||||
64 | covidex.sim | covidex | feedback | UNJUDGED | 0.3254 | 0.3829 | 0.3511 | 0.4546 | 0.1567 | report |