|  | MRR@100, test queries | ar | bn | en | fi | id | ja | ko | ru | sw | te | th |  | avg | 
    
    
|  | BM25 | 0.368 | 0.418 | 0.140 | 0.284 | 0.376 | 0.212 | 0.285 | 0.316 | 0.389 | 0.528 | 0.401 |  | 0.338 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ar \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic \
  --output run.mrtydi.bm25.ar.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-arabic-test \
  run.mrtydi.bm25.ar.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language bn \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali \
  --output run.mrtydi.bm25.bn.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-bengali-test \
  run.mrtydi.bm25.bn.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language en \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english \
  --output run.mrtydi.bm25.en.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-english-test \
  run.mrtydi.bm25.en.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language fi \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish \
  --output run.mrtydi.bm25.fi.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-finnish-test \
  run.mrtydi.bm25.fi.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language id \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian \
  --output run.mrtydi.bm25.id.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-indonesian-test \
  run.mrtydi.bm25.id.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ja \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese \
  --output run.mrtydi.bm25.ja.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-japanese-test \
  run.mrtydi.bm25.ja.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ko \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean \
  --output run.mrtydi.bm25.ko.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-korean-test \
  run.mrtydi.bm25.ko.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ru \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian \
  --output run.mrtydi.bm25.ru.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-russian-test \
  run.mrtydi.bm25.ru.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language sw \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili \
  --output run.mrtydi.bm25.sw.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-swahili-test \
  run.mrtydi.bm25.sw.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language te \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu \
  --output run.mrtydi.bm25.te.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-telugu-test \
  run.mrtydi.bm25.te.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language th \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai \
  --output run.mrtydi.bm25.th.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-thai-test \
  run.mrtydi.bm25.th.test.txt
 | 
|  | mDPR (split encoders), pre-FT w/ NQ | 0.291 | 0.296 | 0.291 | 0.205 | 0.271 | 0.212 | 0.234 | 0.282 | 0.188 | 0.110 | 0.171 |  | 0.232 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-split-pft-nq.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-split-pft-nq.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-split-pft-nq.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-split-pft-nq.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-split-pft-nq.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-split-pft-nq.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-split-pft-nq.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-split-pft-nq.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-split-pft-nq.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-split-pft-nq.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-split-pft-nq.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ NQ | 0.221 | 0.254 | 0.243 | 0.244 | 0.281 | 0.206 | 0.223 | 0.250 | 0.262 | 0.097 | 0.158 |  | 0.222 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-nq.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-nq.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-nq.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-nq.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-nq.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-nq.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-nq.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-nq.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-nq.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-nq.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-nq.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ MS MARCO | 0.441 | 0.397 | 0.327 | 0.275 | 0.352 | 0.311 | 0.282 | 0.356 | 0.342 | 0.310 | 0.269 |  | 0.333 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-msmarco.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-msmarco.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-msmarco.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-msmarco.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-msmarco.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-msmarco.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-msmarco.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ MS MARCO, FT w/ all | 0.695 | 0.623 | 0.492 | 0.559 | 0.578 | 0.501 | 0.486 | 0.516 | 0.644 | 0.891 | 0.618 |  | 0.600 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -M 100 -m recip_rank mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.th.test.txt
 | 
    
  
 
 
  
    
      
        |  | Recall@100, test queries | ar | bn | en | fi | id | ja | ko | ru | sw | te | th |  | avg | 
    
    
|  | BM25 | 0.793 | 0.869 | 0.536 | 0.720 | 0.843 | 0.643 | 0.619 | 0.654 | 0.764 | 0.897 | 0.853 |  | 0.745 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ar \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic \
  --output run.mrtydi.bm25.ar.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-arabic-test \
  run.mrtydi.bm25.ar.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language bn \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali \
  --output run.mrtydi.bm25.bn.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-bengali-test \
  run.mrtydi.bm25.bn.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language en \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english \
  --output run.mrtydi.bm25.en.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-english-test \
  run.mrtydi.bm25.en.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language fi \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish \
  --output run.mrtydi.bm25.fi.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-finnish-test \
  run.mrtydi.bm25.fi.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language id \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian \
  --output run.mrtydi.bm25.id.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-indonesian-test \
  run.mrtydi.bm25.id.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ja \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese \
  --output run.mrtydi.bm25.ja.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-japanese-test \
  run.mrtydi.bm25.ja.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ko \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean \
  --output run.mrtydi.bm25.ko.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-korean-test \
  run.mrtydi.bm25.ko.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language ru \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian \
  --output run.mrtydi.bm25.ru.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-russian-test \
  run.mrtydi.bm25.ru.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language sw \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili \
  --output run.mrtydi.bm25.sw.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-swahili-test \
  run.mrtydi.bm25.sw.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language te \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu \
  --output run.mrtydi.bm25.te.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-telugu-test \
  run.mrtydi.bm25.te.test.txt
Command to generate run:
   
python -m pyserini.search.lucene \
  --threads 16 --batch-size 128 \
  --language th \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai \
  --output run.mrtydi.bm25.th.test.txt --bm25 --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-thai-test \
  run.mrtydi.bm25.th.test.txt
 | 
|  | mDPR (split encoders), pre-FT w/ NQ | 0.650 | 0.793 | 0.678 | 0.568 | 0.685 | 0.584 | 0.532 | 0.647 | 0.528 | 0.366 | 0.515 |  | 0.595 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-split-pft-nq.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-split-pft-nq.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-split-pft-nq.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-split-pft-nq.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-split-pft-nq.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-split-pft-nq.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-split-pft-nq.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-split-pft-nq.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-split-pft-nq.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-split-pft-nq.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder castorini/mdpr-question-nq \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-nq \
  --output run.mrtydi.mdpr-split-pft-nq.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-split-pft-nq.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ NQ | 0.600 | 0.707 | 0.689 | 0.640 | 0.691 | 0.573 | 0.550 | 0.618 | 0.597 | 0.245 | 0.455 |  | 0.579 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-nq.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-nq.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-nq.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-nq.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-nq.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-nq.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-nq.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-nq.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-nq.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-nq.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-nq \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-nq \
  --output run.mrtydi.mdpr-tied-pft-nq.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-nq.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ MS MARCO | 0.797 | 0.784 | 0.754 | 0.647 | 0.736 | 0.732 | 0.617 | 0.743 | 0.634 | 0.782 | 0.595 |  | 0.711 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-msmarco.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-msmarco.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-msmarco.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-msmarco.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-msmarco.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-msmarco.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-msmarco.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-msmarco \
  --output run.mrtydi.mdpr-tied-pft-msmarco.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-msmarco.th.test.txt
 | 
|  | mDPR (tied encoders), pre-FT w/ MS MARCO, FT w/ all | 0.900 | 0.955 | 0.841 | 0.856 | 0.861 | 0.813 | 0.785 | 0.843 | 0.876 | 0.966 | 0.883 |  | 0.871 | 
|  |  | 
  
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-arabic-test \
  --index mrtydi-v1.1-arabic-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ar.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-arabic-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ar.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-bengali-test \
  --index mrtydi-v1.1-bengali-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.bn.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-bengali-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.bn.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-english-test \
  --index mrtydi-v1.1-english-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.en.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-english-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.en.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-finnish-test \
  --index mrtydi-v1.1-finnish-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.fi.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-finnish-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.fi.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-indonesian-test \
  --index mrtydi-v1.1-indonesian-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.id.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-indonesian-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.id.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-japanese-test \
  --index mrtydi-v1.1-japanese-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ja.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-japanese-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ja.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-korean-test \
  --index mrtydi-v1.1-korean-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ko.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-korean-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ko.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-russian-test \
  --index mrtydi-v1.1-russian-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ru.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-russian-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.ru.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-swahili-test \
  --index mrtydi-v1.1-swahili-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.sw.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-swahili-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.sw.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-telugu-test \
  --index mrtydi-v1.1-telugu-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.te.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-telugu-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.te.test.txt
Command to generate run:
   
python -m pyserini.search.faiss \
  --threads 16 --batch-size 512 \
  --encoder-class auto \
  --encoder castorini/mdpr-tied-pft-msmarco-ft-all \
  --topics mrtydi-v1.1-thai-test \
  --index mrtydi-v1.1-thai-mdpr-tied-pft-msmarco-ft-all \
  --output run.mrtydi.mdpr-tied-pft-msmarco-ft-all.th.test.txt --hits 100
 
Evaluation commands:
   
python -m pyserini.eval.trec_eval \
  -c -m recall.100 mrtydi-v1.1-thai-test \
  run.mrtydi.mdpr-tied-pft-msmarco-ft-all.th.test.txt
 | 
    
  
 
  
  
  Programmatic Execution
  All experimental runs shown in the above table can be programmatically executed based on the instructions below.
  To list all the experimental conditions:
  
  python -m pyserini.2cr.mrtydi --list-conditions
  
  Run all languages for a specific condition and show commands:
  
  python -m pyserini.2cr.mrtydi --condition bm25 --display-commands
  
  Run a particular language for a specific condition and show commands:
  
  python -m pyserini.2cr.mrtydi --condition bm25 --language ko --display-commands
  
  Run all languages for all conditions and show commands:
  
  python -m pyserini.2cr.mrtydi --all --display-commands
  
  With the above commands, run files will be placed in the current directory. Use the option --directory runs to place the runs in a sub-directory.
  For a specific condition, just show the commands and do not run:
  
  python -m pyserini.2cr.mrtydi --condition bm25 --display-commands --dry-run
  
  This will generate exactly the commands for a specific condition above (corresponding to a row in the table).
  For a specific condition and language, just show the commands and do not run:
  
  python -m pyserini.2cr.mrtydi --condition bm25 --language ko --display-commands --dry-run
  
  For all conditions, just show the commands and do not run and skip evaluation:
  
  python -m pyserini.2cr.mrtydi --all --display-commands --dry-run --skip-eval
  
  Finally, to generate this page:
  
  python -m pyserini.2cr.mrtydi --generate-report --output docs/2cr/mrtydi.html
  
  The output file mrtydi.html should be identical to this page.