Skip to content

Latest commit

 

History

History
142 lines (103 loc) · 9.03 KB

regressions-msmarco-passage-unicoil.md

File metadata and controls

142 lines (103 loc) · 9.03 KB
Raw

Anserini Regressions: MS MARCO Passage Ranking

Model: uniCOIL (with doc2query-T5 expansions)

This page describes regression experiments, integrated into Anserini's regression testing framework, using uniCOIL (with doc2query-T5 expansions) on the MS MARCO passage ranking task. 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. arXiv:2106.14807.

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 msmarco-passage-unicoil

We make available a version of the MS MARCO Passage Corpus that has already been processed with uniCOIL, i.e., we have applied doc2query-T5 expansions, performed model inference on every document, and stored the output sparse vectors. Thus, no neural inference is involved.

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 msmarco-passage-unicoil

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/JIMMYLIN-bucket0/data/msmarco-passage-unicoil.tar -P collections/
tar xvf collections/msmarco-passage-unicoil.tar -C collections/

To confirm, msmarco-passage-unicoil.tar is 3.4 GB and has MD5 checksum 78eef752c78c8691f7d61600ceed306f. With the corpus downloaded, the following command will perform the remaining steps below:

python src/main/python/run_regression.py --index --verify --search --regression msmarco-passage-unicoil \
  --corpus-path collections/msmarco-passage-unicoil

Indexing

Sample indexing command:

target/appassembler/bin/IndexCollection \
  -collection JsonVectorCollection \
  -input /path/to/msmarco-passage-unicoil \
  -generator DefaultLuceneDocumentGenerator \
  -index indexes/lucene-index.msmarco-passage-unicoil/ \
  -threads 16 -impact -pretokenized -storeDocvectors \
  >& logs/log.msmarco-passage-unicoil &

The path /path/to/msmarco-passage-unicoil/ should point to the corpus downloaded above.

The important indexing options to note here are -impact -pretokenized: the first tells Anserini not to encode BM25 doclengths into Lucene's norms (which is the default) and the second option says not to apply any additional tokenization on the uniCOIL tokens. Upon completion, we should have an index with 8,841,823 documents.

For additional details, see explanation of common indexing options.

Retrieval

Topics and qrels are stored here, which is linked to the Anserini repo as a submodule. The regression experiments here evaluate on the 6980 dev set questions; see this page for more details.

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

target/appassembler/bin/SearchCollection \
  -index indexes/lucene-index.msmarco-passage-unicoil/ \
  -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.unicoil.tsv.gz \
  -topicReader TsvInt \
  -output runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt \
  -impact -pretokenized &

Evaluation can be performed using trec_eval:

target/appassembler/bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt
target/appassembler/bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt
target/appassembler/bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt
target/appassembler/bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt

Effectiveness

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

AP@1000 uniCOIL (with doc2query-T5 expansions)
MS MARCO Passage: Dev 0.3574
RR@10 uniCOIL (with doc2query-T5 expansions)
MS MARCO Passage: Dev 0.3516
R@100 uniCOIL (with doc2query-T5 expansions)
MS MARCO Passage: Dev 0.8609
R@1000 uniCOIL (with doc2query-T5 expansions)
MS MARCO Passage: Dev 0.9582

The above runs are in TREC output format and evaluated with trec_eval. In order to reproduce results reported in the paper, we need to convert to MS MARCO output format and then evaluate:

python tools/scripts/msmarco/convert_trec_to_msmarco_run.py \
   --input runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt \
   --output runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.tsv --quiet

python tools/scripts/msmarco/msmarco_passage_eval.py \
   tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt \
   runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.tsv

The results should be as follows:

#####################
MRR @10: 0.35155222404147896
QueriesRanked: 6980
#####################

This corresponds to the effectiveness reported in the paper and also the run named "uniCOIL-d2q" on the official MS MARCO Passage Ranking Leaderboard, submitted 2021/09/22.

Reproduction Log*

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