22 datasets found
  1. h

    Data from: fiqa

    • huggingface.co
    Updated Aug 16, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2023). fiqa [Dataset]. https://huggingface.co/datasets/BeIR/fiqa
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 16, 2023
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/fiqa.

  2. h

    nfcorpus

    • huggingface.co
    Updated Aug 16, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2023). nfcorpus [Dataset]. https://huggingface.co/datasets/BeIR/nfcorpus
    Explore at:
    Dataset updated
    Aug 16, 2023
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/nfcorpus.

  3. h

    scifact

    • huggingface.co
    Updated Aug 16, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2023). scifact [Dataset]. https://huggingface.co/datasets/BeIR/scifact
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 16, 2023
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scifact.

  4. h

    scidocs

    • huggingface.co
    Updated Aug 16, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2023). scidocs [Dataset]. https://huggingface.co/datasets/BeIR/scidocs
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 16, 2023
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scidocs.

  5. h

    quora

    • huggingface.co
    Updated Aug 16, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2023). quora [Dataset]. https://huggingface.co/datasets/BeIR/quora
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 16, 2023
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/quora.

  6. h

    hotpotqa-qrels

    • huggingface.co
    Updated Aug 12, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). hotpotqa-qrels [Dataset]. https://huggingface.co/datasets/BeIR/hotpotqa-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 12, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/hotpotqa-qrels.

  7. h

    scidocs-generated-queries

    • huggingface.co
    Updated Jun 25, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). scidocs-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/scidocs-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Jun 25, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scidocs-generated-queries.

  8. h

    hotpotqa-generated-queries

    • huggingface.co
    Updated Aug 9, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). hotpotqa-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/hotpotqa-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 9, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/hotpotqa-generated-queries.

  9. h

    fiqa-generated-queries

    • huggingface.co
    Updated Oct 6, 2017
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2017). fiqa-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/fiqa-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Oct 6, 2017
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/fiqa-generated-queries.

  10. h

    fiqa-qrels

    • huggingface.co
    Updated Sep 18, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). fiqa-qrels [Dataset]. https://huggingface.co/datasets/BeIR/fiqa-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Sep 18, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/fiqa-qrels.

  11. h

    scidocs-qrels

    • huggingface.co
    Updated Aug 10, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). scidocs-qrels [Dataset]. https://huggingface.co/datasets/BeIR/scidocs-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 10, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scidocs-qrels.

  12. h

    scifact-qrels

    • huggingface.co
    • opendatalab.com
    Updated Aug 12, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). scifact-qrels [Dataset]. https://huggingface.co/datasets/BeIR/scifact-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 12, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scifact-qrels.

  13. h

    scifact-generated-queries

    • huggingface.co
    Updated Jun 25, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). scifact-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/scifact-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Jun 25, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/scifact-generated-queries.

  14. h

    nfcorpus-qrels

    • huggingface.co
    • opendatalab.com
    Updated Aug 11, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). nfcorpus-qrels [Dataset]. https://huggingface.co/datasets/BeIR/nfcorpus-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 11, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/nfcorpus-qrels.

  15. h

    quora-generated-queries

    • huggingface.co
    Updated Aug 12, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). quora-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/quora-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 12, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/quora-generated-queries.

  16. h

    beir

    • huggingface.co
    Updated Feb 3, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). beir [Dataset]. https://huggingface.co/datasets/BeIR/beir
    Explore at:
    Dataset updated
    Feb 3, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/beir.

  17. h

    hotpotqa

    • huggingface.co
    Updated Aug 24, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). hotpotqa [Dataset]. https://huggingface.co/datasets/BeIR/hotpotqa
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 24, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/hotpotqa.

  18. h

    nq-generated-queries

    • huggingface.co
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR, nq-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/nq-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/nq-generated-queries.

  19. h

    nq-qrels

    • huggingface.co
    • opendatalab.com
    Updated Aug 28, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). nq-qrels [Dataset]. https://huggingface.co/datasets/BeIR/nq-qrels
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 28, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/nq-qrels.

  20. h

    nfcorpus-generated-queries

    • huggingface.co
    Updated Aug 8, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    BEIR (2022). nfcorpus-generated-queries [Dataset]. https://huggingface.co/datasets/BeIR/nfcorpus-generated-queries
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Aug 8, 2022
    Dataset authored and provided by
    BEIR
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Dataset Card for BEIR Benchmark

      Dataset Summary

    BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

    Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/nfcorpus-generated-queries.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
BEIR (2023). fiqa [Dataset]. https://huggingface.co/datasets/BeIR/fiqa

Data from: fiqa

BeIR/fiqa

BEIR Benchmark

Related Article
Explore at:
CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
Dataset updated
Aug 16, 2023
Dataset authored and provided by
BEIR
License

Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
License information was derived automatically

Description

Dataset Card for BEIR Benchmark

  Dataset Summary

BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:

Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval: TREC-NEWS, Robust04 Argument Retrieval: Touche-2020, ArguAna Duplicate Question Retrieval: Quora, CqaDupstack Citation-Prediction: SCIDOCS Tweet… See the full description on the dataset page: https://huggingface.co/datasets/BeIR/fiqa.

Search
Clear search
Close search
Google apps
Main menu