Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Install RAG24 baseline + update docs #2638

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Install RAG24 baseline + update docs #2638

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 22 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ Each of these [_end-to-end_ regressions](docs/regressions.md) starts from the ra
See individual pages for details.

<details>
<summary>MS MARCO V1 Passage Regressions</summary>
<summary>MS MARCO V1 Passage Regressions (dev queries, TREC DL 19/20)</summary>

### MS MARCO V1 Passage Regressions

Expand Down Expand Up @@ -168,7 +168,7 @@ Key:

</details>
<details>
<summary>MS MARCO V1 Document Regressions</summary>
<summary>MS MARCO V1 Document Regressions (dev queries, TREC DL 19/20)</summary>

### MS MARCO V1 Document Regressions

Expand Down Expand Up @@ -198,7 +198,7 @@ Key:

</details>
<details>
<summary>MS MARCO V2 Passage Regressions</summary>
<summary>MS MARCO V2 Passage Regressions (dev/dev2 queries, TREC DL 21/22/23)</summary>

### MS MARCO V2 Passage Regressions

Expand Down Expand Up @@ -229,7 +229,7 @@ Key:

</details>
<details>
<summary>MS MARCO V2 Document Regressions</summary>
<summary>MS MARCO V2 Document Regressions (dev/dev2 queries, TREC DL 21/22/23)</summary>

### MS MARCO V2 Document Regressions

Expand All @@ -254,12 +254,28 @@ Key:

</details>
<details>
<summary>MS MARCO V2.1 Document Regressions</summary>
<summary>MS MARCO V2.1 Passage Regressions (TREC RAG 24)</summary>

### MS MARCO V2.1 Passage Regressions

The MS MARCO V2.1 corpora were derived from the V2 corpora for the TREC 2024 RAG Track.
Instructions for downloading the corpus can be found [here](https://trec-rag.github.io/annoucements/2024-corpus-finalization/).
The experiments below use _passage-level_ qrels.

| | RAG 24 |
|-----------|:-------------------------------------------------------------:|
| baselines | [+](docs/regressions/regressions-rag24-doc-segmented-test.md) |

</details>
<details>
<summary>MS MARCO V2.1 Document Regressions (dev set for TREC RAG 24)</summary>

### MS MARCO V2.1 Document Regressions

The MS MARCO V2.1 corpora were derived from the V2 corpora for the TREC 2024 RAG Track.
The experiments below capture topics and qrels originally targeted at the V2 corpora, but have been "projected" over to the V2.1 corpora.
Instructions for downloading the corpus can be found [here](https://trec-rag.github.io/annoucements/2024-corpus-finalization/).
The experiments below capture topics and _document-level_ qrels originally targeted at the V2 corpora, but have been "projected" over to the V2.1 corpora.
These should be treated like dev topics for the TREC 2024 RAG Track; actual qrels for that track were generated at the passage level.

| | dev | DL21 | DL22 | DL23 | RAGgy dev |
|-----------------------------------------|:---------------------------------------------------------------:|:--------------------------------------------------------------------:|:--------------------------------------------------------------------:|:--------------------------------------------------------------------:|:------------------------------------------------------------------:|
Expand Down
264 changes: 263 additions & 1 deletion docs/regressions.md
View file
Open in desktop

Large diffs are not rendered by default.

5 changes: 0 additions & 5 deletions docs/regressions/regressions-dl21-doc-segmented-msmarco-v2.1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,8 +101,3 @@ With the above commands, you should be able to reproduce the following results:
| [DL21 (Doc)](https://microsoft.github.io/msmarco/TREC-Deep-Learning) | 0.3811 | 0.4200 | 0.4260 |
| **R@1000** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [DL21 (Doc)](https://microsoft.github.io/msmarco/TREC-Deep-Learning) | 0.7115 | 0.7839 | 0.7924 |

Some of these regressions correspond to official TREC 2021 Deep Learning Track "baseline" submissions:

+ `dseg_bm25` = BM25 (default), `k1=0.9`, `b=0.4`
+ `dseg_bm25rm3` = BM25 (default) + RM3, `k1=0.9`, `b=0.4`
4 changes: 2 additions & 2 deletions docs/regressions/regressions-rag24-doc-segmented-test.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,9 @@

**Models**: various bag-of-words approaches on segmented documents

This page describes regression experiments for document ranking _on the segmented version_ of the MS MARCO V2.1 document corpus using the test queries, which is integrated into Anserini's regression testing framework.
This page describes regression experiments for document ranking _on the segmented version_ of the MS MARCO V2.1 document corpus using the test topics (= queries in TREC parlance), which is integrated into Anserini's regression testing framework.
This corpus was derived from the MS MARCO V2 _segmented_ document corpus and prepared for the TREC 2024 RAG Track.
Instructions for downloading the corpus can be found [here](https://trec-rag.github.io/annoucements/2024-corpus-finalization/).

Here, we cover bag-of-words baselines where each _segment_ in the MS MARCO V2.1 segmented document corpus is treated as a unit of indexing.

Expand Down Expand Up @@ -38,7 +39,6 @@ For additional details, see explanation of [common indexing options](../../docs/
## Retrieval

Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/tree/master/topics-and-qrels), which is linked to the Anserini repo as a submodule.
These evaluation resources are from the original V2 corpus, but have been "projected" over to the V2.1 corpus.

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

Expand Down
6 changes: 5 additions & 1 deletion src/main/python/regressions-batch03.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
# TREC RAG 24
python src/main/python/run_regression.py --index --verify --search --regression rag24-doc-segmented-test > logs/log.rag24-doc-segmented-test 2>&1

python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.bge-base-en-v1.5.flat.cached > logs/log.msmarco-v1-passage.bge-base-en-v1.5.flat.cached.txt 2>&1
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached > logs/log.msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached.txt 2>&1
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cos-dpr-distil.flat.cached > logs/log.msmarco-v1-passage.cos-dpr-distil.flat.cached.txt 2>&1
Expand All @@ -8,8 +11,9 @@ python src/main/python/run_regression.py --index --verify --search --regression
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cos-dpr-distil.flat-int8.cached > logs/log.msmarco-v1-passage.cos-dpr-distil.flat-int8.cached.txt 2>&1
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.openai-ada2.flat-int8.cached > logs/log.msmarco-v1-passage.openai-ada2.flat-int8.cached.txt 2>&1

# MS MARCO V2.1 (note we already built doc segmented from RAG 24 above)
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v2.1-doc > logs/log.msmarco-v2.1-doc.txt 2>&1
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v2.1-doc-segmented > logs/log.msmarco-v2.1-doc-segmented.txt 2>&1
python src/main/python/run_regression.py --verify --search --regression msmarco-v2.1-doc-segmented > logs/log.msmarco-v2.1-doc-segmented.txt 2>&1

# MS MARCO V1 passage
python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cohere-embed-english-v3.0.hnsw.cached > logs/log.msmarco-v1-passage.cohere-embed-english-v3.0.hnsw.cached.txt 2>&1
Expand Down
5 changes: 0 additions & 5 deletions src/main/resources/docgen/templates/dl21-doc-segmented-msmarco-v2.1.template
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,8 +52,3 @@ ${eval_cmds}
With the above commands, you should be able to reproduce the following results:

${effectiveness}

Some of these regressions correspond to official TREC 2021 Deep Learning Track "baseline" submissions:

+ `dseg_bm25` = BM25 (default), `k1=0.9`, `b=0.4`
+ `dseg_bm25rm3` = BM25 (default) + RM3, `k1=0.9`, `b=0.4`
4 changes: 2 additions & 2 deletions src/main/resources/docgen/templates/rag24-doc-segmented-test.template
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,9 @@

**Models**: various bag-of-words approaches on segmented documents

This page describes regression experiments for document ranking _on the segmented version_ of the MS MARCO V2.1 document corpus using the test queries, which is integrated into Anserini's regression testing framework.
This page describes regression experiments for document ranking _on the segmented version_ of the MS MARCO V2.1 document corpus using the test topics (= queries in TREC parlance), which is integrated into Anserini's regression testing framework.
This corpus was derived from the MS MARCO V2 _segmented_ document corpus and prepared for the TREC 2024 RAG Track.
Instructions for downloading the corpus can be found [here](https://trec-rag.github.io/annoucements/2024-corpus-finalization/).

Here, we cover bag-of-words baselines where each _segment_ in the MS MARCO V2.1 segmented document corpus is treated as a unit of indexing.

Expand Down Expand Up @@ -31,7 +32,6 @@ For additional details, see explanation of [common indexing options](${root_path
## Retrieval

Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/tree/master/topics-and-qrels), which is linked to the Anserini repo as a submodule.
These evaluation resources are from the original V2 corpus, but have been "projected" over to the V2.1 corpus.

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

Expand Down
Loading