← home
Github: datasets/msmarco_passage.py

ir_datasets: MSMARCO (passage)

Index
  1. msmarco-passage
  2. msmarco-passage/dev
  3. msmarco-passage/dev/judged
  4. msmarco-passage/dev/small
  5. msmarco-passage/eval
  6. msmarco-passage/eval/small
  7. msmarco-passage/train
  8. msmarco-passage/train/judged
  9. msmarco-passage/train/medical
  10. msmarco-passage/train/split200-train
  11. msmarco-passage/train/split200-valid
  12. msmarco-passage/trec-dl-2019
  13. msmarco-passage/trec-dl-2019/judged
  14. msmarco-passage/trec-dl-2020
  15. msmarco-passage/trec-dl-2020/judged
  16. msmarco-passage/trec-dl-hard
  17. msmarco-passage/trec-dl-hard/fold1
  18. msmarco-passage/trec-dl-hard/fold2
  19. msmarco-passage/trec-dl-hard/fold3
  20. msmarco-passage/trec-dl-hard/fold4
  21. msmarco-passage/trec-dl-hard/fold5

"msmarco-passage"

A passage ranking benchmark with a collection of 8.8 million passages and question queries. Most relevance judgments are shallow (typically at most 1-2 per query), but the TREC Deep Learning track adds deep judgments. Evaluation typically conducted using MRR@10.

Note that the original document source files for this collection contain a double-encoding error that cause strange sequences like "å¬" and "ðºð". These are automatically corrrected (properly converting previous examples to "公" and "🇺🇸").

docs

Language: en

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/dev"

Official dev set.

scoreddocs are the top 1000 results from BM25. These are used for the "re-ranking" setting. Note that these are sub-sampled to about 1/8 of the total avaialable dev queries by the MSMARCO authors for faster evaluation. The BM25 scores from scoreddocs are not available (all have a score of 0).

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/dev/judged"

Subset of msmarco-passage/dev that only includes queries that have at least one qrel.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/judged")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/judged queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/judged")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/judged docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/judged')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/judged")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/judged qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/judged")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/judged scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/dev/small"

Official "small" version of the dev set, consisting of 6,980 queries (6.9% of the full dev set).

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/small")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/small queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/small')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/small")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/small docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/small')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/dev/small")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/dev/small qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/dev/small')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/eval"

Official eval set for submission to MS MARCO leaderboard. Relevance judgments are hidden.

scoreddocs are the top 1000 results from BM25. These are used for the "re-ranking" setting. Note that these are sub-sampled to about 1/8 of the total avaialable eval queries by the MSMARCO authors for faster evaluation. The BM25 scores from scoreddocs are not available (all have a score of 0).

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/eval")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/eval queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/eval')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/eval")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/eval docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/eval')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/eval")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/eval scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/eval/small"

Official "small" version of the eval set, consisting of 6,837 queries (6.8% of the full eval set).

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/eval/small")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/eval/small queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/eval/small')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/eval/small")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/eval/small docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/eval/small')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/train"

Official train set.

Not all queries have relevance judgments. Use msmarco-passage/train/judged for a filtered list that only includes documents that have at least one qrel.

scoreddocs are the top 1000 results from BM25. These are used for the "re-ranking" setting. Note that these are sub-sampled to about 1/8 of the total avaialable train queries by the MSMARCO authors for faster evaluation. The BM25 scores from scoreddocs are not available (all have a score of 0).

docpairs provides access to the "official" sequence for pairwise training.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

docpairs
Document Pair type:
GenericDocPair: (namedtuple)
  1. query_id: str
  2. doc_id_a: str
  3. doc_id_b: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train")
for docpair in dataset.docpairs_iter():
    docpair # namedtuple<query_id, doc_id_a, doc_id_b>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train docpairs
[query_id]    [doc_id_a]    [doc_id_b]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/train/judged"

Subset of msmarco-passage/train that only includes queries that have at least one qrel.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/judged")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/judged queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/judged")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/judged docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/judged')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/judged")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/judged qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/judged")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/judged scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

docpairs
Document Pair type:
GenericDocPair: (namedtuple)
  1. query_id: str
  2. doc_id_a: str
  3. doc_id_b: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/judged")
for docpair in dataset.docpairs_iter():
    docpair # namedtuple<query_id, doc_id_a, doc_id_b>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/judged docpairs
[query_id]    [doc_id_a]    [doc_id_b]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/train/medical"

Subset of msmarco-passage/train that only includes queries that have a layman or expert medical term. Note that this includes about 20% false matches due to terms with multiple senses.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/medical")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/medical queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/medical')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/medical")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/medical docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/medical')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/medical")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/medical qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/medical')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/medical")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/medical scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

docpairs
Document Pair type:
GenericDocPair: (namedtuple)
  1. query_id: str
  2. doc_id_a: str
  3. doc_id_b: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/medical")
for docpair in dataset.docpairs_iter():
    docpair # namedtuple<query_id, doc_id_a, doc_id_b>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/medical docpairs
[query_id]    [doc_id_a]    [doc_id_b]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{MacAvaney2020MedMarco,Bajaj2016Msmarco}

Bibtex:

@inproceedings{MacAvaney2020MedMarco, author = {MacAvaney, Sean and Cohan, Arman and Goharian, Nazli}, title = {SLEDGE-Zero: A Zero-Shot Baseline for COVID-19 Literature Search}, booktitle = {EMNLP}, year = {2020} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/train/split200-train"

Subset of msmarco-passage/train without 200 queries that are meant to be used as a small validation set. From various works.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-train")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-train queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-train')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-train")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-train docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-train')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-train")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-train qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-train')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-train")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-train scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

docpairs
Document Pair type:
GenericDocPair: (namedtuple)
  1. query_id: str
  2. doc_id_a: str
  3. doc_id_b: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-train")
for docpair in dataset.docpairs_iter():
    docpair # namedtuple<query_id, doc_id_a, doc_id_b>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-train docpairs
[query_id]    [doc_id_a]    [doc_id_b]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/train/split200-valid"

Subset of msmarco-passage/train with only 200 queries that are meant to be used as a small validation set. From various works.

Official evaluation measures: RR@10

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-valid")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-valid queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-valid')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-valid")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-valid docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-valid')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1Labeled by crowd worker as relevant

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-valid")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-valid qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/train/split200-valid')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [RR@10]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-valid")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-valid scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

docpairs
Document Pair type:
GenericDocPair: (namedtuple)
  1. query_id: str
  2. doc_id_a: str
  3. doc_id_b: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/train/split200-valid")
for docpair in dataset.docpairs_iter():
    docpair # namedtuple<query_id, doc_id_a, doc_id_b>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/train/split200-valid docpairs
[query_id]    [doc_id_a]    [doc_id_b]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Bajaj2016Msmarco}

Bibtex:

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-2019"

Queries from the TREC Deep Learning (DL) 2019 shared task, which were sampled from msmarco-passage/eval. A subset of these queries were judged by NIST assessors, (filtered list available in msmarco-passage/trec-dl-2019/judged).

Official evaluation measures: nDCG@10, RR(rel=2), AP(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2), AP(rel=2)]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019 scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Craswell2019TrecDl,Bajaj2016Msmarco}

Bibtex:

@inproceedings{Craswell2019TrecDl, title={Overview of the TREC 2019 deep learning track}, author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos and Ellen Voorhees}, booktitle={TREC 2019}, year={2019} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-2019/judged"

Subset of msmarco-passage/trec-dl-2019, only including queries with qrels.

Official evaluation measures: nDCG@10, RR(rel=2), AP(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019/judged")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019/judged queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019/judged")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019/judged docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019/judged')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019/judged")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019/judged qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2019/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2), AP(rel=2)]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2019/judged")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2019/judged scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Craswell2019TrecDl,Bajaj2016Msmarco}

Bibtex:

@inproceedings{Craswell2019TrecDl, title={Overview of the TREC 2019 deep learning track}, author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos and Ellen Voorhees}, booktitle={TREC 2019}, year={2019} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-2020"

Queries from the TREC Deep Learning (DL) 2020 shared task, which were sampled from msmarco-passage/eval. A subset of these queries were judged by NIST assessors, (filtered list available in msmarco-passage/trec-dl-2020/judged).

Official evaluation measures: nDCG@10, RR(rel=2), AP(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2), AP(rel=2)]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020 scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Craswell2020TrecDl,Bajaj2016Msmarco}

Bibtex:

@inproceedings{Craswell2020TrecDl, title={Overview of the TREC 2020 deep learning track}, author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos}, booktitle={TREC}, year={2020} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-2020/judged"

Subset of msmarco-passage/trec-dl-2020, only including queries with qrels.

Official evaluation measures: nDCG@10, RR(rel=2), AP(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020/judged")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020/judged queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020/judged")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020/judged docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020/judged')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020/judged")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020/judged qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-2020/judged')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2), AP(rel=2)]
)

You can find more details about PyTerrier experiments here.

scoreddocs
Scored Document type:
GenericScoredDoc: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. score: float

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-2020/judged")
for scoreddoc in dataset.scoreddocs_iter():
    scoreddoc # namedtuple<query_id, doc_id, score>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-2020/judged scoreddocs --format tsv
[query_id]    [doc_id]    [score]
...

You can find more details about the CLI here.

PyTerrier

No example available for PyTerrier

Citation

ir_datasets.bib:

\cite{Craswell2020TrecDl,Bajaj2016Msmarco}

Bibtex:

@inproceedings{Craswell2020TrecDl, title={Overview of the TREC 2020 deep learning track}, author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos}, booktitle={TREC}, year={2020} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard/fold1"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold1")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold1 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold1')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold1")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold1 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold1')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold1")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold1 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold1')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard/fold2"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold2")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold2 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold2')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold2")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold2 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold2')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold2")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold2 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold2')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard/fold3"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold3")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold3 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold3')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold3")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold3 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold3')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold3")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold3 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold3')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard/fold4"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold4")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold4 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold4')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold4")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold4 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold4')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold4")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold4 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold4')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

"msmarco-passage/trec-dl-hard/fold5"

A more challenging subset of msmarco-passage/trec-dl-2019 and msmarco-document/trec-dl-2020.

Official evaluation measures: nDCG@10, RR(rel=2)

queries

Language: en

Query type:
GenericQuery: (namedtuple)
  1. query_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold5")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold5 queries
[query_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold5')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics())

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from msmarco-passage

Document type:
GenericDoc: (namedtuple)
  1. doc_id: str
  2. text: str

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold5")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, text>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold5 docs
[doc_id]    [text]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold5')
# Index msmarco-passage
indexer = pt.IterDictIndexer('./indices/msmarco-passage')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['text'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
0Irrelevant: The passage has nothing to do with the query.
1Related: The passage seems related to the query but does not answer it.
2Highly relevant: The passage has some answer for the query, but the answer may be a bit unclear, or hidden amongst extraneous information.
3Perfectly relevant: The passage is dedicated to the query and contains the exact answer.

Examples:

Python API
import ir_datasets
dataset = ir_datasets.load("msmarco-passage/trec-dl-hard/fold5")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI
ir_datasets export msmarco-passage/trec-dl-hard/fold5 qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:msmarco-passage/trec-dl-hard/fold5')
index_ref = pt.IndexRef.of('./indices/msmarco-passage') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics(),
    dataset.get_qrels(),
    [nDCG@10, RR(rel=2)]
)

You can find more details about PyTerrier experiments here.

Citation

ir_datasets.bib:

\cite{Mackie2021DlHard,Bajaj2016Msmarco}

Bibtex:

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }