From 27485486229bdc9d5f2bfaed594ca47f0b32b5b3 Mon Sep 17 00:00:00 2001 From: Jimmy Lin Date: Mon, 27 Nov 2023 20:44:18 -0500 Subject: [PATCH] Update docs for SPLADE++ ED regressions on BEIR (#2279) --- docs/regressions-log.md | 6 +++++ docs/regressions.md | 36 +++++++++++++++++++++++++ src/main/python/regressions-batch04.txt | 31 +++++++++++++++++++++ 3 files changed, 73 insertions(+) diff --git a/docs/regressions-log.md b/docs/regressions-log.md index 12ca18e2db..ea4791930f 100644 --- a/docs/regressions-log.md +++ b/docs/regressions-log.md @@ -3,6 +3,12 @@ The following change log details commits to regression tests that alter effectiveness and the addition of new regression tests. This documentation is useful for figuring why results may have changed over time. +### November 24, 2023 + ++ commit [`d88446`](https://github.com/castorini/anserini/commit/d88446c7e0ef344d2e185a7280a999a28ff70662) (11/24/2023) + +Added regressions for SPLADE++ CoCondenser-EnsembleDistil on BEIR (v1.0.0), + ### November 9, 2023 + commit [`d152e5`](https://github.com/castorini/anserini/commit/d152e5a3233483e97aa733a6d18c8b83811d7aff) (11/9/2023) diff --git a/docs/regressions.md b/docs/regressions.md index a806407475..dec59541f6 100644 --- a/docs/regressions.md +++ b/docs/regressions.md @@ -189,6 +189,42 @@ nohup python src/main/python/run_regression.py --index --verify --search --regre ``` +
+BEIR (v1.0.0): SPLADE++ CoCondenser-EnsembleDistil + +```bash +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-trec-covid-splade-pp-ed >& logs/log.beir-v1.0.0-trec-covid-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-bioasq-splade-pp-ed >& logs/log.beir-v1.0.0-bioasq-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-nfcorpus-splade-pp-ed >& logs/log.beir-v1.0.0-nfcorpus-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-nq-splade-pp-ed >& logs/log.beir-v1.0.0-nq-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-hotpotqa-splade-pp-ed >& logs/log.beir-v1.0.0-hotpotqa-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-fiqa-splade-pp-ed >& logs/log.beir-v1.0.0-fiqa-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-signal1m-splade-pp-ed >& logs/log.beir-v1.0.0-signal1m-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-trec-news-splade-pp-ed >& logs/log.beir-v1.0.0-trec-news-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-robust04-splade-pp-ed >& logs/log.beir-v1.0.0-robust04-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-arguana-splade-pp-ed >& logs/log.beir-v1.0.0-arguana-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-webis-touche2020-splade-pp-ed >& logs/log.beir-v1.0.0-webis-touche2020-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-android-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-android-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-english-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-english-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-gaming-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-gaming-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-gis-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-gis-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-mathematica-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-mathematica-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-physics-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-physics-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-programmers-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-programmers-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-stats-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-stats-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-tex-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-tex-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-unix-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-unix-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-webmasters-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-webmasters-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-wordpress-splade-pp-ed >& logs/log.beir-v1.0.0-cqadupstack-wordpress-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-quora-splade-pp-ed >& logs/log.beir-v1.0.0-quora-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-dbpedia-entity-splade-pp-ed >& logs/log.beir-v1.0.0-dbpedia-entity-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-scidocs-splade-pp-ed >& logs/log.beir-v1.0.0-scidocs-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-fever-splade-pp-ed >& logs/log.beir-v1.0.0-fever-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-climate-fever-splade-pp-ed >& logs/log.beir-v1.0.0-climate-fever-splade-pp-ed & +nohup python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-scifact-splade-pp-ed >& logs/log.beir-v1.0.0-scifact-splade-pp-ed & +``` +
+
BEIR (v1.0.0): SPLADE-distill CoCodenser-medium diff --git a/src/main/python/regressions-batch04.txt b/src/main/python/regressions-batch04.txt index 375c707545..fda36474e7 100644 --- a/src/main/python/regressions-batch04.txt +++ b/src/main/python/regressions-batch04.txt @@ -3,6 +3,37 @@ python src/main/python/run_regression.py --index --verify --search --regression python src/main/python/run_regression.py --index --verify --search --regression car17v2.0 > logs/log.car17v2.0 2>&1 python src/main/python/run_regression.py --index --verify --search --regression car17v2.0-doc2query > logs/log.car17v2.0-doc2query 2>&1 +# BEIR: SPLADE++ ED +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-trec-covid-splade-pp-ed > logs/log.beir-v1.0.0-trec-covid-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-bioasq-splade-pp-ed > logs/log.beir-v1.0.0-bioasq-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-nfcorpus-splade-pp-ed > logs/log.beir-v1.0.0-nfcorpus-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-nq-splade-pp-ed > logs/log.beir-v1.0.0-nq-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-hotpotqa-splade-pp-ed > logs/log.beir-v1.0.0-hotpotqa-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-fiqa-splade-pp-ed > logs/log.beir-v1.0.0-fiqa-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-signal1m-splade-pp-ed > logs/log.beir-v1.0.0-signal1m-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-trec-news-splade-pp-ed > logs/log.beir-v1.0.0-trec-news-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-robust04-splade-pp-ed > logs/log.beir-v1.0.0-robust04-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-arguana-splade-pp-ed > logs/log.beir-v1.0.0-arguana-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-webis-touche2020-splade-pp-ed > logs/log.beir-v1.0.0-webis-touche2020-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-android-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-android-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-english-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-english-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-gaming-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-gaming-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-gis-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-gis-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-mathematica-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-mathematica-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-physics-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-physics-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-programmers-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-programmers-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-stats-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-stats-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-tex-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-tex-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-unix-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-unix-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-webmasters-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-webmasters-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-cqadupstack-wordpress-splade-pp-ed > logs/log.beir-v1.0.0-cqadupstack-wordpress-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-quora-splade-pp-ed > logs/log.beir-v1.0.0-quora-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-dbpedia-entity-splade-pp-ed > logs/log.beir-v1.0.0-dbpedia-entity-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-scidocs-splade-pp-ed > logs/log.beir-v1.0.0-scidocs-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-fever-splade-pp-ed > logs/log.beir-v1.0.0-fever-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-climate-fever-splade-pp-ed > logs/log.beir-v1.0.0-climate-fever-splade-pp-ed 2>&1 +python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-scifact-splade-pp-ed > logs/log.beir-v1.0.0-scifact-splade-pp-ed 2>&1 + # Newswire python src/main/python/run_regression.py --index --verify --search --regression disk12 > logs/log.disk12 2>&1 python src/main/python/run_regression.py --index --verify --search --regression disk45 > logs/log.disk45 2>&1