Dataset Overview

Dataset Name

msmarco-document-v2/trec-dl-2019

Data Source

• Source dataset: irds/msmarco-document-v2

Task Category

• Text Retrieval

Data Content

• queries (query topics): count = 200
• qrels (relevance judgments): count = 13,940
• docs: use the irds/msmarco-document-v2 dataset

Usage

from datasets import load_dataset

queries = load_dataset(irds/msmarco-document-v2_trec-dl-2019, queries)
for record in queries:
    record # {query_id: ..., text: ...}

qrels = load_dataset(irds/msmarco-document-v2_trec-dl-2019, qrels)
for record in qrels:
    record # {query_id: ..., doc_id: ..., relevance: ..., iteration: ...}

Citation Information

@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={6​016} }