Skip to content

Latest commit

 

History

History
117 lines (83 loc) · 7.22 KB

regressions-dl20-passage.openai-ada2.flat-int8.cached.md

File metadata and controls

117 lines (83 loc) · 7.22 KB

Anserini Regressions: TREC 2020 Deep Learning Track (Passage)

Model: OpenAI-ada2 embeddings with quantized flat indexes (using cached queries)

This page describes regression experiments, integrated into Anserini's regression testing framework, using OpenAI-ada2 embeddings on the TREC 2020 Deep Learning Track passage ranking task, as described in the following paper:

Jimmy Lin, Ronak Pradeep, Tommaso Teofili, and Jasper Xian. Vector Search with OpenAI Embeddings: Lucene Is All You Need. arXiv:2308.14963, 2023.

In these experiments, we are using cached queries (i.e., cached results of query encoding).

Note that the NIST relevance judgments provide far more relevant passages per topic, unlike the "sparse" judgments provided by Microsoft (these are sometimes called "dense" judgments to emphasize this contrast). For additional instructions on working with MS MARCO passage collection, refer to this page.

The exact configurations for these regressions are stored in this YAML file. Note that this page is automatically generated from this template as part of Anserini's regression pipeline, so do not modify this page directly; modify the template instead and then run bin/build.sh to rebuild the documentation.

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 dl20-passage.openai-ada2.flat-int8.cached

We make available a version of the MS MARCO Passage Corpus that has already been encoded with the OpenAI-ada2 embedding model.

From any machine, the following command will download the corpus and perform the complete regression, end to end:

python src/main/python/run_regression.py --download --index --verify --search --regression dl20-passage.openai-ada2.flat-int8.cached

The run_regression.py script automates the following steps, but if you want to perform each step manually, simply copy/paste from the commands below and you'll obtain the same regression results.

Corpus Download

Download the corpus and unpack into collections/:

wget https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-openai-ada2.tar -P collections/
tar xvf collections/msmarco-passage-openai-ada2.tar -C collections/

To confirm, msmarco-passage-openai-ada2.tar is 109 GB and has MD5 checksum a4d843d522ff3a3af7edbee789a63402. With the corpus downloaded, the following command will perform the remaining steps below:

python src/main/python/run_regression.py --index --verify --search --regression dl20-passage.openai-ada2.flat-int8.cached \
  --corpus-path collections/msmarco-passage-openai-ada2

Indexing

Sample indexing command, building quantized flat indexes:

bin/run.sh io.anserini.index.IndexFlatDenseVectors \
  -threads 16 \
  -collection JsonDenseVectorCollection \
  -input /path/to/msmarco-passage-openai-ada2 \
  -generator DenseVectorDocumentGenerator \
  -index indexes/lucene-flat-int8.msmarco-v1-passage.openai-ada2/ \
  -quantize.int8 \
  >& logs/log.msmarco-passage-openai-ada2 &

The path /path/to/msmarco-passage-openai-ada2/ should point to the corpus downloaded above. Upon completion, we should have an index with 8,841,823 documents.

Retrieval

Topics and qrels are stored here, which is linked to the Anserini repo as a submodule. The regression experiments here evaluate on the 54 topics for which NIST has provided judgments as part of the TREC 2020 Deep Learning Track. The original data can be found here.

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

bin/run.sh io.anserini.search.SearchFlatDenseVectors \
  -index indexes/lucene-flat-int8.msmarco-v1-passage.openai-ada2/ \
  -topics tools/topics-and-qrels/topics.dl20.openai-ada2.jsonl.gz \
  -topicReader JsonIntVector \
  -output runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-int8-cached.topics.dl20.openai-ada2.jsonl.txt \
  -hits 1000 -threads 16 &

Evaluation can be performed using trec_eval:

bin/trec_eval -m map -c -l 2 tools/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-int8-cached.topics.dl20.openai-ada2.jsonl.txt
bin/trec_eval -m ndcg_cut.10 -c tools/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-int8-cached.topics.dl20.openai-ada2.jsonl.txt
bin/trec_eval -m recall.100 -c -l 2 tools/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-int8-cached.topics.dl20.openai-ada2.jsonl.txt
bin/trec_eval -m recall.1000 -c -l 2 tools/topics-and-qrels/qrels.dl20-passage.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-int8-cached.topics.dl20.openai-ada2.jsonl.txt

Effectiveness

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

AP@1000 OpenAI-ada2
DL20 (Passage) 0.4771
nDCG@10 OpenAI-ada2
DL20 (Passage) 0.6759
R@100 OpenAI-ada2
DL20 (Passage) 0.7237
R@1000 OpenAI-ada2
DL20 (Passage) 0.8705

The above figures are from running brute-force search with cached queries on non-quantized indexes. With cached queries on quantized indexes, results may differ slightly.

❗ Retrieval metrics here are computed to depth 1000 hits per query (as opposed to 100 hits per query for document ranking). For computing nDCG, remember that we keep qrels of all relevance grades, whereas for other metrics (e.g., AP), relevance grade 1 is considered not relevant (i.e., use the -l 2 option in trec_eval). The experimental results reported here are directly comparable to the results reported in the track overview paper.

Reproduction Log*

To add to this reproduction log, modify this template and run bin/build.sh to rebuild the documentation.