-
Notifications
You must be signed in to change notification settings - Fork 478
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add unicoil-noexp on beir datasets (#1913)
add all required to run unicoil-noexp on beir (29) datasets including: (1) add unicoil-noexp pre-encoded queries (2) documents (3) integration test
- Loading branch information
Showing
119 changed files
with
5,202 additions
and
34 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — ArguAna | ||
|
|
||
| **Model**: uniCOIL (without any expansions) | ||
|
|
||
| This page describes regression experiments, integrated into Anserini's regression testing framework, using uniCOIL (without any expansions) on [BEIR (v1.0.0) — ArguAna](http://beir.ai/). | ||
| The uniCOIL model is described in the following paper: | ||
|
|
||
| > Jimmy Lin and Xueguang Ma. [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques.](https://arxiv.org/abs/2106.14807) _arXiv:2106.14807_. | ||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-arguana-unicoil-noexp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-arguana-unicoil-noexp.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-arguana-unicoil-noexp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection JsonVectorCollection \ | ||
| -input /path/to/beir-v1.0.0-arguana-unicoil-noexp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-arguana-unicoil-noexp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 16 -impact -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-arguana-unicoil-noexp & | ||
| ``` | ||
|
|
||
| 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-arguana-unicoil-noexp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-arguana.test.unicoil-noexp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-arguana-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-arguana.test.unicoil-noexp.txt \ | ||
| -impact -pretokenized -removeQuery -hits 1000 & | ||
| ``` | ||
|
|
||
| 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-arguana.test.txt runs/run.beir-v1.0.0-arguana-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-arguana.test.unicoil-noexp.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-arguana.test.txt runs/run.beir-v1.0.0-arguana-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-arguana.test.unicoil-noexp.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-arguana.test.txt runs/run.beir-v1.0.0-arguana-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-arguana.test.unicoil-noexp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.3959 | | ||
|
|
||
|
|
||
| | R@100 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.9225 | | ||
|
|
||
|
|
||
| | R@1000 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.9794 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — BioASQ | ||
|
|
||
| **Model**: uniCOIL (without any expansions) | ||
|
|
||
| This page describes regression experiments, integrated into Anserini's regression testing framework, using uniCOIL (without any expansions) on [BEIR (v1.0.0) — BioASQ](http://beir.ai/). | ||
| The uniCOIL model is described in the following paper: | ||
|
|
||
| > Jimmy Lin and Xueguang Ma. [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques.](https://arxiv.org/abs/2106.14807) _arXiv:2106.14807_. | ||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-bioasq-unicoil-noexp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-bioasq-unicoil-noexp.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-unicoil-noexp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection JsonVectorCollection \ | ||
| -input /path/to/beir-v1.0.0-bioasq-unicoil-noexp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-bioasq-unicoil-noexp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 16 -impact -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-bioasq-unicoil-noexp & | ||
| ``` | ||
|
|
||
| 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-unicoil-noexp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.unicoil-noexp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-bioasq-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-bioasq.test.unicoil-noexp.txt \ | ||
| -impact -pretokenized -removeQuery -hits 1000 & | ||
| ``` | ||
|
|
||
| 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-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-bioasq.test.unicoil-noexp.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-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-bioasq.test.unicoil-noexp.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-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-bioasq.test.unicoil-noexp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): BioASQ | 0.4771 | | ||
|
|
||
|
|
||
| | R@100 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): BioASQ | 0.7306 | | ||
|
|
||
|
|
||
| | R@1000 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): BioASQ | 0.8814 | |
72 changes: 72 additions & 0 deletions
72
docs/regressions-beir-v1.0.0-climate-fever-unicoil-noexp.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — Climate-FEVER | ||
|
|
||
| **Model**: uniCOIL (without any expansions) | ||
|
|
||
| This page describes regression experiments, integrated into Anserini's regression testing framework, using uniCOIL (without any expansions) on [BEIR (v1.0.0) — Climate-FEVER](http://beir.ai/). | ||
| The uniCOIL model is described in the following paper: | ||
|
|
||
| > Jimmy Lin and Xueguang Ma. [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques.](https://arxiv.org/abs/2106.14807) _arXiv:2106.14807_. | ||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-climate-fever-unicoil-noexp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-climate-fever-unicoil-noexp.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-climate-fever-unicoil-noexp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection JsonVectorCollection \ | ||
| -input /path/to/beir-v1.0.0-climate-fever-unicoil-noexp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-climate-fever-unicoil-noexp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 16 -impact -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-climate-fever-unicoil-noexp & | ||
| ``` | ||
|
|
||
| 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-climate-fever-unicoil-noexp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-climate-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.txt \ | ||
| -impact -pretokenized -removeQuery -hits 1000 & | ||
| ``` | ||
|
|
||
| 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-climate-fever.test.txt runs/run.beir-v1.0.0-climate-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.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-climate-fever.test.txt runs/run.beir-v1.0.0-climate-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.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-climate-fever.test.txt runs/run.beir-v1.0.0-climate-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.1824 | | ||
|
|
||
|
|
||
| | R@100 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.4182 | | ||
|
|
||
|
|
||
| | R@1000 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.5849 | |
72 changes: 72 additions & 0 deletions
72
docs/regressions-beir-v1.0.0-cqadupstack-android-unicoil-noexp.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — CQADupStack-android | ||
|
|
||
| **Model**: uniCOIL (without any expansions) | ||
|
|
||
| This page describes regression experiments, integrated into Anserini's regression testing framework, using uniCOIL (without any expansions) on [BEIR (v1.0.0) — CQADupStack-android](http://beir.ai/). | ||
| The uniCOIL model is described in the following paper: | ||
|
|
||
| > Jimmy Lin and Xueguang Ma. [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques.](https://arxiv.org/abs/2106.14807) _arXiv:2106.14807_. | ||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-cqadupstack-android-unicoil-noexp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-cqadupstack-android-unicoil-noexp.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-cqadupstack-android-unicoil-noexp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection JsonVectorCollection \ | ||
| -input /path/to/beir-v1.0.0-cqadupstack-android-unicoil-noexp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-unicoil-noexp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 16 -impact -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-cqadupstack-android-unicoil-noexp & | ||
| ``` | ||
|
|
||
| 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-cqadupstack-android-unicoil-noexp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-cqadupstack-android-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.txt \ | ||
| -impact -pretokenized -removeQuery -hits 1000 & | ||
| ``` | ||
|
|
||
| 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-cqadupstack-android.test.txt runs/run.beir-v1.0.0-cqadupstack-android-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.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-cqadupstack-android.test.txt runs/run.beir-v1.0.0-cqadupstack-android-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.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-cqadupstack-android.test.txt runs/run.beir-v1.0.0-cqadupstack-android-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.3563 | | ||
|
|
||
|
|
||
| | R@100 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.6464 | | ||
|
|
||
|
|
||
| | R@1000 | uniCOIL no expansion| | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.8361 | |
Oops, something went wrong.