Rename msmarco-passage -> msmarco-passage-wp in YAML for wp-based reg…

…ressions (#1858) Otherwise, if we run the "base" and "wp" versions concurrently, they clash with each other.
castorini · Apr 26, 2022 · 38cd408 · 38cd408
1 parent d4155e2
commit 38cd408
Show file tree

Hide file tree

Showing 6 changed files with 24 additions and 24 deletions.
diff --git a/docs/regressions-dl19-passage-wp.md b/docs/regressions-dl19-passage-wp.md
@@ -25,11 +25,11 @@ Typical indexing command:
 ```
 target/appassembler/bin/IndexCollection \
   -collection JsonCollection \
-  -input /path/to/msmarco-passage \
+  -input /path/to/msmarco-passage-wp \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -generator DefaultLuceneDocumentGenerator \
   -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \
-  >& logs/log.msmarco-passage &
+  >& logs/log.msmarco-passage-wp &
 ```
 
 The directory `/path/to/msmarco-passage-wp/` should be a directory containing the corpus in Anserini's jsonl format.
@@ -49,17 +49,17 @@ target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -topics src/main/resources/topics-and-qrels/topics.dl19-passage.wp.tsv.gz \
   -topicreader TsvInt \
-  -output runs/run.msmarco-passage.bm25-default.topics.dl19-passage.wp.txt \
+  -output runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt \
   -bm25 -pretokenized &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```
-tools/eval/trec_eval.9.0.4/trec_eval -m map -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl19-passage.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m ndcg_cut.10 -c src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl19-passage.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m recall.100 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl19-passage.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m recall.1000 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl19-passage.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m map -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m ndcg_cut.10 -c src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m recall.100 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m recall.1000 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl19-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt
 ```
 
 ## Effectiveness

diff --git a/docs/regressions-dl20-passage-wp.md b/docs/regressions-dl20-passage-wp.md
@@ -25,11 +25,11 @@ Typical indexing command:
 ```
 target/appassembler/bin/IndexCollection \
   -collection JsonCollection \
-  -input /path/to/msmarco-passage \
+  -input /path/to/msmarco-passage-wp \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -generator DefaultLuceneDocumentGenerator \
   -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \
-  >& logs/log.msmarco-passage &
+  >& logs/log.msmarco-passage-wp &
 ```
 
 The directory `/path/to/msmarco-passage-wp/` should be a directory containing the corpus in Anserini's jsonl format.
@@ -49,17 +49,17 @@ target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -topics src/main/resources/topics-and-qrels/topics.dl20.wp.tsv.gz \
   -topicreader TsvInt \
-  -output runs/run.msmarco-passage.bm25-default.topics.dl20.wp.txt \
+  -output runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt \
   -bm25 -pretokenized &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```
-tools/eval/trec_eval.9.0.4/trec_eval -m map -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl20.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m ndcg_cut.10 -c src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl20.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m recall.100 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl20.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -m recall.1000 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage.bm25-default.topics.dl20.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m map -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m ndcg_cut.10 -c src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m recall.100 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -m recall.1000 -c -l 2 src/main/resources/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt
 ```
 
 ## Effectiveness

diff --git a/docs/regressions-msmarco-passage-wp.md b/docs/regressions-msmarco-passage-wp.md
@@ -22,11 +22,11 @@ Typical indexing command:
 ```
 target/appassembler/bin/IndexCollection \
   -collection JsonCollection \
-  -input /path/to/msmarco-passage \
+  -input /path/to/msmarco-passage-wp \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -generator DefaultLuceneDocumentGenerator \
   -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \
-  >& logs/log.msmarco-passage &
+  >& logs/log.msmarco-passage-wp &
 ```
 
 The directory `/path/to/msmarco-passage-wp/` should be a directory containing the corpus in Anserini's jsonl format.
@@ -45,17 +45,17 @@ target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.msmarco-passage-wp/ \
   -topics src/main/resources/topics-and-qrels/topics.msmarco-passage.dev-subset.wp.tsv.gz \
   -topicreader TsvInt \
-  -output runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.wp.txt \
+  -output runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt \
   -bm25 -pretokenized &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```
-tools/eval/trec_eval.9.0.4/trec_eval -c -m map src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m map src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 src/main/resources/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt
 ```
 
 ## Effectiveness

diff --git a/src/main/resources/regression/dl19-passage-wp.yaml b/src/main/resources/regression/dl19-passage-wp.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage
+corpus: msmarco-passage-wp
 corpus_path: collections/msmarco/msmarco-passage-wp
 
 index_path: indexes/lucene-index.msmarco-passage-wp/

diff --git a/src/main/resources/regression/dl20-passage-wp.yaml b/src/main/resources/regression/dl20-passage-wp.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage
+corpus: msmarco-passage-wp
 corpus_path: collections/msmarco/msmarco-passage-wp
 
 index_path: indexes/lucene-index.msmarco-passage-wp/

diff --git a/src/main/resources/regression/msmarco-passage-wp.yaml b/src/main/resources/regression/msmarco-passage-wp.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage
+corpus: msmarco-passage-wp
 corpus_path: collections/msmarco/msmarco-passage-wp
 
 index_path: indexes/lucene-index.msmarco-passage-wp/