Rename Faiss indexes to be consistent with current naming scheme (cas…

…torini#1498)

docs/experiments-ance.md

@@ -14,7 +14,7 @@ Thus, while the scoring script provides results to much higher precision, we hav
 
 ```bash
 python -m pyserini.search.faiss \
-  --index msmarco-passage-ance-bf \
+  --index msmarco-v1-passage.ance \
   --topics msmarco-passage-dev-subset \
   --encoded-queries ance-msmarco-passage-dev-subset \
   --output runs/run.msmarco-passage.ance.bf.tsv \
@@ -58,7 +58,7 @@ recall_1000           	all	0.9584
 
 ```bash
 python -m pyserini.search.faiss \
-  --index msmarco-doc-ance-maxp-bf \
+  --index msmarco-v1-doc.ance-maxp \
   --topics msmarco-doc-dev \
   --encoded-queries ance_maxp-msmarco-doc-dev \
   --output runs/run.msmarco-doc.passage.ance-maxp.txt \
@@ -103,7 +103,7 @@ recall_100            	all	0.9033
 
 ```bash
 python -m pyserini.search.faiss \
-  --index wikipedia-ance-multi-bf \
+  --index wikipedia-dpr-100w.ance-multi \
   --topics dpr-nq-test \
   --encoded-queries ance_multi-nq-test \
   --output runs/run.ance.nq-test.multi.bf.trec \
@@ -117,7 +117,7 @@ To evaluate, first convert the TREC output format to DPR's `json` format:
 ```bash
 $ python -m pyserini.eval.convert_trec_run_to_dpr_retrieval_run \
     --topics dpr-nq-test \
-    --index wikipedia-dpr \
+    --index wikipedia-dpr-100w \
     --input runs/run.ance.nq-test.multi.bf.trec \
     --output runs/run.ance.nq-test.multi.bf.json
 
@@ -135,7 +135,7 @@ Top100	accuracy: 0.8787
 
 ```bash
 python -m pyserini.search.faiss \
-  --index wikipedia-ance-multi-bf \
+  --index wikipedia-dpr-100w.ance-multi \
   --topics dpr-trivia-test \
   --encoded-queries ance_multi-trivia-test \
   --output runs/run.ance.trivia-test.multi.bf.trec \
@@ -149,7 +149,7 @@ To evaluate, first convert the TREC output format to DPR's `json` format:
 ```bash
 $ python -m pyserini.eval.convert_trec_run_to_dpr_retrieval_run \
     --topics dpr-trivia-test \
-    --index wikipedia-dpr \
+    --index wikipedia-dpr-100w \
     --input runs/run.ance.trivia-test.multi.bf.trec \
     --output runs/run.ance.trivia-test.multi.bf.json
 

docs/experiments-bpr.md

@@ -24,7 +24,7 @@ BPR with brute-force index:
 
 ```bash
 python -m pyserini.search.faiss \
-  --index wikipedia-bpr-single-nq-hash \
+  --index wikipedia-dpr-100w.bpr-single-nq \
   --topics dpr-nq-test \
   --encoded-queries bpr_single_nq-nq-test \
   --output runs/run.bpr.rerank.nq-test.nq.hash.trec \
@@ -39,7 +39,7 @@ To evaluate, first convert the TREC output format to DPR's `json` format:
 
 ```bash
 $ python -m pyserini.eval.convert_trec_run_to_dpr_retrieval_run \
-    --index wikipedia-dpr \
+    --index wikipedia-dpr-100w \
     --topics dpr-nq-test \
     --input runs/run.bpr.rerank.nq-test.nq.hash.trec \
     --output runs/run.bpr.rerank.nq-test.nq.hash.json

docs/experiments-distilbert_kd.md

@@ -12,10 +12,10 @@ Dense retrieval, with brute-force index:
 
 ```bash
 python -m pyserini.search.faiss \
-  --index msmarco-passage-distilbert-dot-margin_mse-T2-bf \
+  --index msmarco-v1-passage.distilbert-dot-margin-mse-t2 \
   --topics msmarco-passage-dev-subset \
   --encoded-queries distilbert_kd-msmarco-passage-dev-subset \
-  --output runs/run.msmarco-passage.distilbert-dot-margin_mse-T2.bf.tsv \
+  --output runs/run.msmarco-passage.distilbert-dot-margin_mse-t2.bf.tsv \
   --output-format msmarco \
   --batch-size 36 --threads 12
 ```
@@ -26,7 +26,7 @@ To evaluate:
 
 ```bash
 $ python -m pyserini.eval.msmarco_passage_eval msmarco-passage-dev-subset \
-    runs/run.msmarco-passage.distilbert-dot-margin_mse-T2.bf.tsv
+    runs/run.msmarco-passage.distilbert-dot-margin_mse-t2.bf.tsv
 
 #####################
 MRR @10: 0.3250
@@ -39,11 +39,11 @@ For that we first need to convert runs and qrels files to the TREC format:
 
 ```bash
 $ python -m pyserini.eval.convert_msmarco_run_to_trec_run \
-    --input runs/run.msmarco-passage.distilbert-dot-margin_mse-T2.bf.tsv \
-    --output runs/run.msmarco-passage.distilbert-dot-margin_mse-T2.bf.trec
+    --input runs/run.msmarco-passage.distilbert-dot-margin_mse-t2.bf.tsv \
+    --output runs/run.msmarco-passage.distilbert-dot-margin_mse-t2.bf.trec
 
 $ python -m pyserini.eval.trec_eval -c -mrecall.1000 -mmap msmarco-passage-dev-subset \
-    runs/run.msmarco-passage.distilbert-dot-margin_mse-T2.bf.trec
+    runs/run.msmarco-passage.distilbert-dot-margin_mse-t2.bf.trec
 
 map                     all     0.3308
 recall_1000             all     0.9553

docs/experiments-distilbert_tasb.md

@@ -12,7 +12,7 @@ Dense retrieval, with brute-force index:
 
 ```bash
 python -m pyserini.search.faiss \
-  --index msmarco-passage-distilbert-dot-tas_b-b256-bf \
+  --index msmarco-v1-passage.distilbert-dot-tas_b-b256 \
   --topics msmarco-passage-dev-subset \
   --encoded-queries distilbert_tas_b-msmarco-passage-dev-subset \
   --output runs/run.msmarco-passage.distilbert-dot-tas_b-b256.bf.tsv \