Skip to content

Commit

Permalink
Add remaining BEIR multifield regressions (#1859)
Browse files Browse the repository at this point in the history
* add beir_v1.0.0 multifield regressions in README

* Add regression docs for beir_v1.0.0 multifield

* Add docgen templates for beir_v1.0.0 multifield

* Add regression yaml files for beir_v1.0.0 multifield
  • Loading branch information
thakur-nandan authored Apr 26, 2022
1 parent 38cd408 commit 7adee1d
Show file tree
Hide file tree
Showing 63 changed files with 3,260 additions and 30 deletions.
38 changes: 19 additions & 19 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -105,32 +105,32 @@ See individual pages for details!
+ Regressions for Mr. TyDi (v1.1) baselines : [ar](docs/regressions-mrtydi-v1.1-ar.md), [bn](docs/regressions-mrtydi-v1.1-bn.md), [en](docs/regressions-mrtydi-v1.1-en.md), [fi](docs/regressions-mrtydi-v1.1-fi.md), [id](docs/regressions-mrtydi-v1.1-id.md), [ja](docs/regressions-mrtydi-v1.1-ja.md), [ko](docs/regressions-mrtydi-v1.1-ko.md), [ru](docs/regressions-mrtydi-v1.1-ru.md), [sw](docs/regressions-mrtydi-v1.1-sw.md), [te](docs/regressions-mrtydi-v1.1-te.md), [th](docs/regressions-mrtydi-v1.1-th.md)
+ Regressions for BEIR (v1.0.0):
+ TREC-COVID: ["flat" baseline](docs/regressions-beir-v1.0.0-trec-covid-flat.md), ["multfield" baseline](docs/regressions-beir-v1.0.0-trec-covid-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-trec-covid-splade-distil-cocodenser-medium.md)
+ BioASQ: ["flat" baseline](docs/regressions-beir-v1.0.0-bioasq-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md)
+ BioASQ: ["flat" baseline](docs/regressions-beir-v1.0.0-bioasq-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-bioasq-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md)
+ NFCorpus: ["flat" baseline](docs/regressions-beir-v1.0.0-nfcorpus-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-nfcorpus-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-nfcorpus-splade-distil-cocodenser-medium.md)
+ NQ: ["flat" baseline](docs/regressions-beir-v1.0.0-nq-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-nq-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-nq-splade-distil-cocodenser-medium.md)
+ HotpotQA: ["flat" baseline](docs/regressions-beir-v1.0.0-hotpotqa-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md)
+ HotpotQA: ["flat" baseline](docs/regressions-beir-v1.0.0-hotpotqa-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-hotpotqa-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md)
+ FiQA-2018: ["flat" baseline](docs/regressions-beir-v1.0.0-fiqa-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-fiqa-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-fiqa-splade-distil-cocodenser-medium.md)
+ Signal-1M(RT): ["flat" baseline](docs/regressions-beir-v1.0.0-signal1m-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md)
+ Signal-1M(RT): ["flat" baseline](docs/regressions-beir-v1.0.0-signal1m-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-signal1m-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md)
+ TREC-NEWS: ["flat" baseline](docs/regressions-beir-v1.0.0-trec-news-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-trec-news-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-trec-news-splade-distil-cocodenser-medium.md)
+ Robust04: ["flat" baseline](docs/regressions-beir-v1.0.0-robust04-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-robust04-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-robust04-splade-distil-cocodenser-medium.md)
+ ArguAna: ["flat" baseline](docs/regressions-beir-v1.0.0-arguana-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-arguana-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-arguana-splade-distil-cocodenser-medium.md)
+ Touche2020: ["flat" baseline](docs/regressions-beir-v1.0.0-webis-touche2020-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md)
+ CQADupStack-Android: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-android-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md)
+ CQADupStack-English: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-english-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md)
+ CQADupStack-Gaming: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md)
+ CQADupStack-Gis: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gis-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md)
+ CQADupStack-Mathematica: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md)
+ CQADupStack-Physics: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-physics-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md)
+ CQADupStack-Programmers: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md)
+ CQADupStack-Stats: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-stats-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md)
+ CQADupStack-Tex: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-tex-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md)
+ CQADupStack-Unix: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-unix-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md)
+ CQADupStack-Webmasters: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md)
+ CQADupStack-Wordpress: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md)
+ Quora: ["flat" baseline](docs/regressions-beir-v1.0.0-quora-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md)
+ DBPedia: ["flat" baseline](docs/regressions-beir-v1.0.0-dbpedia-entity-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md)
+ Touche2020: ["flat" baseline](docs/regressions-beir-v1.0.0-webis-touche2020-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-arguana-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md)
+ CQADupStack-Android: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-android-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-android-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md)
+ CQADupStack-English: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-english-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-english-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md)
+ CQADupStack-Gaming: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gaming-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md)
+ CQADupStack-Gis: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gis-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-gis-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md)
+ CQADupStack-Mathematica: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-mathematica-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md)
+ CQADupStack-Physics: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-physics-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-physics-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md)
+ CQADupStack-Programmers: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-programmers-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md)
+ CQADupStack-Stats: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-stats-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-stats-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md)
+ CQADupStack-Tex: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-tex-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-tex-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md)
+ CQADupStack-Unix: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-unix-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-unix-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md)
+ CQADupStack-Webmasters: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-webmasters-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md)
+ CQADupStack-Wordpress: ["flat" baseline](docs/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-cqadupstack-wordpress-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md)
+ Quora: ["flat" baseline](docs/regressions-beir-v1.0.0-quora-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-quora-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md)
+ DBPedia: ["flat" baseline](docs/regressions-beir-v1.0.0-dbpedia-entity-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-dbpedia-entity-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md)
+ SCIDOCS: ["flat" baseline](docs/regressions-beir-v1.0.0-scidocs-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-multifield-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-scidocs-splade-distil-cocodenser-medium.md)
+ FEVER: ["flat" baseline](docs/regressions-beir-v1.0.0-fever-flat.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md)
+ FEVER: ["flat" baseline](docs/regressions-beir-v1.0.0-fever-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-fever-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md)
+ Climate-FEVER: ["flat" baseline](docs/regressions-beir-v1.0.0-climate-fever-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-climate-fever-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-climate-fever-splade-distil-cocodenser-medium.md)
+ SciFact: ["flat" baseline](docs/regressions-beir-v1.0.0-scifact-flat.md), ["multifield" baseline](docs/regressions-beir-v1.0.0-scifact-multifield.md), [SPLADE-distill CoCodenser-medium](docs/regressions-beir-v1.0.0-scifact-splade-distil-cocodenser-medium.md)

Expand Down
4 changes: 2 additions & 2 deletions docs/regressions-beir-v1.0.0-arguana-multifield.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Anserini Regressions: BEIR (v1.0.0) — arguana
# Anserini Regressions: BEIR (v1.0.0) — ArguAna

This page documents BM25 regression experiments for [BEIR (v1.0.0) — arguana](http://beir.ai/).
This page documents BM25 regression experiments for [BEIR (v1.0.0) — ArguAna](http://beir.ai/).
These experiments index the "title" and "text" fields in corpus separately.
At retrieval time, a query is issued across both fields (equally weighted).

Expand Down
69 changes: 69 additions & 0 deletions docs/regressions-beir-v1.0.0-bioasq-multifield.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
# Anserini Regressions: BEIR (v1.0.0) — BioASQ

This page documents BM25 regression experiments for [BEIR (v1.0.0) — BioASQ](http://beir.ai/).
These experiments index the "title" and "text" fields in corpus separately.
At retrieval time, a query is issued across both fields (equally weighted).

The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-bioasq-multifield.yaml).
Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-bioasq-multifield.template) as part of Anserini's regression pipeline, so do not modify this page directly; modify the template instead.

From one of our Waterloo servers (e.g., `orca`), the following command will perform the complete regression, end to end:

```
python src/main/python/run_regression.py --index --verify --search --regression beir-v1.0.0-bioasq-multifield
```

## Indexing

Typical indexing command:

```
target/appassembler/bin/IndexCollection \
-collection BeirMultifieldCollection \
-input /path/to/beir-v1.0.0-bioasq-multifield \
-index indexes/lucene-index.beir-v1.0.0-bioasq-multifield/ \
-generator DefaultLuceneDocumentGenerator \
-threads 1 -storePositions -storeDocvectors -storeRaw -fields title \
>& logs/log.beir-v1.0.0-bioasq-multifield &
```

For additional details, see explanation of [common indexing options](common-indexing-options.md).

## Retrieval

After indexing has completed, you should be able to perform retrieval as follows:

```
target/appassembler/bin/SearchCollection \
-index indexes/lucene-index.beir-v1.0.0-bioasq-multifield/ \
-topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \
-topicreader TsvString \
-output runs/run.beir-v1.0.0-bioasq-multifield.bm25.topics.beir-v1.0.0-bioasq.test.txt \
-bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 &
```

Evaluation can be performed using `trec_eval`:

```
tools/eval/trec_eval.9.0.4/trec_eval -c -m ndcg_cut.10 src/main/resources/topics-and-qrels/qrels.beir-v1.0.0-bioasq.test.txt runs/run.beir-v1.0.0-bioasq-multifield.bm25.topics.beir-v1.0.0-bioasq.test.txt
tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 src/main/resources/topics-and-qrels/qrels.beir-v1.0.0-bioasq.test.txt runs/run.beir-v1.0.0-bioasq-multifield.bm25.topics.beir-v1.0.0-bioasq.test.txt
tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 src/main/resources/topics-and-qrels/qrels.beir-v1.0.0-bioasq.test.txt runs/run.beir-v1.0.0-bioasq-multifield.bm25.topics.beir-v1.0.0-bioasq.test.txt
```

## Effectiveness

With the above commands, you should be able to reproduce the following results:

| nDCG@10 | BM25 |
|:-------------------------------------------------------------------------------------------------------------|-----------|
| BEIR (v1.0.0): bioasq | 0.4646 |


| R@100 | BM25 |
|:-------------------------------------------------------------------------------------------------------------|-----------|
| BEIR (v1.0.0): bioasq | 0.7145 |


| R@1000 | BM25 |
|:-------------------------------------------------------------------------------------------------------------|-----------|
| BEIR (v1.0.0): bioasq | 0.8428 |
8 changes: 4 additions & 4 deletions docs/regressions-beir-v1.0.0-climate-fever-multifield.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Anserini Regressions: BEIR (v1.0.0) — climate-fever
# Anserini Regressions: BEIR (v1.0.0) — Climate-FEVER

This page documents BM25 regression experiments for [BEIR (v1.0.0) — climate-fever](http://beir.ai/).
This page documents BM25 regression experiments for [BEIR (v1.0.0) — Climate-FEVER](http://beir.ai/).
These experiments index the "title" and "text" fields in corpus separately.
At retrieval time, a query is issued across both fields (equally weighted).

Expand All @@ -21,7 +21,7 @@ Typical indexing command:
target/appassembler/bin/IndexCollection \
-collection BeirMultifieldCollection \
-input /path/to/beir-v1.0.0-climate-fever-multifield \
-index indexes/lucene-index.beir-v1.0.0-climate-multifield/ \
-index indexes/lucene-index.beir-v1.0.0-climate-fever-multifield/ \
-generator DefaultLuceneDocumentGenerator \
-threads 1 -storePositions -storeDocvectors -storeRaw -fields title \
>& logs/log.beir-v1.0.0-climate-fever-multifield &
Expand All @@ -35,7 +35,7 @@ After indexing has completed, you should be able to perform retrieval as follows

```
target/appassembler/bin/SearchCollection \
-index indexes/lucene-index.beir-v1.0.0-climate-multifield/ \
-index indexes/lucene-index.beir-v1.0.0-climate-fever-multifield/ \
-topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.tsv.gz \
-topicreader TsvString \
-output runs/run.beir-v1.0.0-climate-fever-multifield.bm25.topics.beir-v1.0.0-climate-fever.test.txt \
Expand Down
Loading

0 comments on commit 7adee1d

Please sign in to comment.