-
Notifications
You must be signed in to change notification settings - Fork 467
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Yuqingxie/add beir word piece (#1880)
* add beir word piece tests and documents Co-authored-by: Jimmy Lin <jimmylin@uwaterloo.ca>
- Loading branch information
Showing
75 changed files
with
4,250 additions
and
0 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 +1,69 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — ArguAna | ||
|
|
||
| This page documents BM25 regression experiments for [BEIR (v1.0.0) — ArguAna](http://beir.ai/). | ||
| These experiments index the corpus in a "flat" manner, by concatenating the "title" and "text" into the "contents" field. | ||
| All the documents and queries are pre-tokenized with `bert-base-uncased` tokenizer. | ||
|
|
||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-arguana-wp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-arguana-wp.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-wp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection BeirFlatCollection \ | ||
| -input /path/to/beir-v1.0.0-arguana-wp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-arguana-wp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-arguana-wp & | ||
| ``` | ||
|
|
||
| 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-wp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-arguana.test.wp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-arguana-wp.bm25.topics.beir-v1.0.0-arguana.test.wp.txt \ | ||
| -bm25 -removeQuery -pretokenized & | ||
| ``` | ||
|
|
||
| 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-wp.bm25.topics.beir-v1.0.0-arguana.test.wp.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-wp.bm25.topics.beir-v1.0.0-arguana.test.wp.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-wp.bm25.topics.beir-v1.0.0-arguana.test.wp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.3639 | | ||
|
|
||
|
|
||
| | R@100 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.8791 | | ||
|
|
||
|
|
||
| | R@1000 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): ArguAna | 0.9602 | |
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 +1,69 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — Climate-FEVER | ||
|
|
||
| This page documents BM25 regression experiments for [BEIR (v1.0.0) — Climate-FEVER](http://beir.ai/). | ||
| These experiments index the corpus in a "flat" manner, by concatenating the "title" and "text" into the "contents" field. | ||
| All the documents and queries are pre-tokenized with `bert-base-uncased` tokenizer. | ||
|
|
||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-climate-fever-wp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-climate-fever-wp.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-wp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection BeirFlatCollection \ | ||
| -input /path/to/beir-v1.0.0-climate-fever-wp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-climate-fever-wp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-climate-fever-wp & | ||
| ``` | ||
|
|
||
| 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-wp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.wp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-climate-fever-wp.bm25.topics.beir-v1.0.0-climate-fever.test.wp.txt \ | ||
| -bm25 -removeQuery -pretokenized & | ||
| ``` | ||
|
|
||
| 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-wp.bm25.topics.beir-v1.0.0-climate-fever.test.wp.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-wp.bm25.topics.beir-v1.0.0-climate-fever.test.wp.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-wp.bm25.topics.beir-v1.0.0-climate-fever.test.wp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.1576 | | ||
|
|
||
|
|
||
| | R@100 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.4077 | | ||
|
|
||
|
|
||
| | R@1000 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): Climate-FEVER | 0.5984 | |
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 +1,69 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — CQADupStack-android | ||
|
|
||
| This page documents BM25 regression experiments for [BEIR (v1.0.0) — CQADupStack-android](http://beir.ai/). | ||
| These experiments index the corpus in a "flat" manner, by concatenating the "title" and "text" into the "contents" field. | ||
| All the documents and queries are pre-tokenized with `bert-base-uncased` tokenizer. | ||
|
|
||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-cqadupstack-android-wp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-cqadupstack-android-wp.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-wp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection BeirFlatCollection \ | ||
| -input /path/to/beir-v1.0.0-cqadupstack-android-wp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-wp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-cqadupstack-android-wp & | ||
| ``` | ||
|
|
||
| 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-wp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.wp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-cqadupstack-android-wp.bm25.topics.beir-v1.0.0-cqadupstack-android.test.wp.txt \ | ||
| -bm25 -removeQuery -pretokenized & | ||
| ``` | ||
|
|
||
| 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-wp.bm25.topics.beir-v1.0.0-cqadupstack-android.test.wp.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-wp.bm25.topics.beir-v1.0.0-cqadupstack-android.test.wp.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-wp.bm25.topics.beir-v1.0.0-cqadupstack-android.test.wp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.3694 | | ||
|
|
||
|
|
||
| | R@100 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.6394 | | ||
|
|
||
|
|
||
| | R@1000 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-android | 0.8447 | |
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 +1,69 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — CQADupStack-english | ||
|
|
||
| This page documents BM25 regression experiments for [BEIR (v1.0.0) — CQADupStack-english](http://beir.ai/). | ||
| These experiments index the corpus in a "flat" manner, by concatenating the "title" and "text" into the "contents" field. | ||
| All the documents and queries are pre-tokenized with `bert-base-uncased` tokenizer. | ||
|
|
||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-cqadupstack-english-wp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-cqadupstack-english-wp.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-english-wp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection BeirFlatCollection \ | ||
| -input /path/to/beir-v1.0.0-cqadupstack-english-wp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-wp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-cqadupstack-english-wp & | ||
| ``` | ||
|
|
||
| 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-english-wp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.wp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-cqadupstack-english-wp.bm25.topics.beir-v1.0.0-cqadupstack-english.test.wp.txt \ | ||
| -bm25 -removeQuery -pretokenized & | ||
| ``` | ||
|
|
||
| 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-english.test.txt runs/run.beir-v1.0.0-cqadupstack-english-wp.bm25.topics.beir-v1.0.0-cqadupstack-english.test.wp.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-english.test.txt runs/run.beir-v1.0.0-cqadupstack-english-wp.bm25.topics.beir-v1.0.0-cqadupstack-english.test.wp.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-english.test.txt runs/run.beir-v1.0.0-cqadupstack-english-wp.bm25.topics.beir-v1.0.0-cqadupstack-english.test.wp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-english | 0.3457 | | ||
|
|
||
|
|
||
| | R@100 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-english | 0.5544 | | ||
|
|
||
|
|
||
| | R@1000 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-english | 0.7243 | |
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 +1,69 @@ | ||
| # Anserini Regressions: BEIR (v1.0.0) — CQADupStack-gaming | ||
|
|
||
| This page documents BM25 regression experiments for [BEIR (v1.0.0) — CQADupStack-gaming](http://beir.ai/). | ||
| These experiments index the corpus in a "flat" manner, by concatenating the "title" and "text" into the "contents" field. | ||
| All the documents and queries are pre-tokenized with `bert-base-uncased` tokenizer. | ||
|
|
||
| The exact configurations for these regressions are stored in [this YAML file](../src/main/resources/regression/beir-v1.0.0-cqadupstack-gaming-wp.yaml). | ||
| Note that this page is automatically generated from [this template](../src/main/resources/docgen/templates/beir-v1.0.0-cqadupstack-gaming-wp.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-gaming-wp | ||
| ``` | ||
|
|
||
| ## Indexing | ||
|
|
||
| Typical indexing command: | ||
|
|
||
| ``` | ||
| target/appassembler/bin/IndexCollection \ | ||
| -collection BeirFlatCollection \ | ||
| -input /path/to/beir-v1.0.0-cqadupstack-gaming-wp \ | ||
| -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-wp/ \ | ||
| -generator DefaultLuceneDocumentGenerator \ | ||
| -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ | ||
| >& logs/log.beir-v1.0.0-cqadupstack-gaming-wp & | ||
| ``` | ||
|
|
||
| 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-gaming-wp/ \ | ||
| -topics src/main/resources/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.wp.tsv.gz \ | ||
| -topicreader TsvString \ | ||
| -output runs/run.beir-v1.0.0-cqadupstack-gaming-wp.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.wp.txt \ | ||
| -bm25 -removeQuery -pretokenized & | ||
| ``` | ||
|
|
||
| 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-gaming.test.txt runs/run.beir-v1.0.0-cqadupstack-gaming-wp.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.wp.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-gaming.test.txt runs/run.beir-v1.0.0-cqadupstack-gaming-wp.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.wp.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-gaming.test.txt runs/run.beir-v1.0.0-cqadupstack-gaming-wp.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.wp.txt | ||
| ``` | ||
|
|
||
| ## Effectiveness | ||
|
|
||
| With the above commands, you should be able to reproduce the following results: | ||
|
|
||
| | nDCG@10 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-gaming | 0.4701 | | ||
|
|
||
|
|
||
| | R@100 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-gaming | 0.7438 | | ||
|
|
||
|
|
||
| | R@1000 | BM25 | | ||
| |:-------------------------------------------------------------------------------------------------------------|-----------| | ||
| | BEIR (v1.0.0): CQADupStack-gaming | 0.8810 | |
Oops, something went wrong.