{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T06:05:39Z","timestamp":1768457139737,"version":"3.49.0"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGIR Forum"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:p>Recent years have seen an increase in the number of publicly available datasets that are released to foster research in question answering systems. In this work, we survey the available datasets and also provide a simple, multi-faceted classification of those datasets. We further survey the most recent evaluation results that form the current state of the art in question answering research by exploring related research challenges and associated online leaderboards. Finally, we provide a discussion around the existing online challenges and provide a wishlist of datasets whose release could benefit question answering research in the future.<\/jats:p>","DOI":"10.1145\/3483382.3483389","type":"journal-article","created":{"date-parts":[[2021,8,20]],"date-time":"2021-08-20T18:04:52Z","timestamp":1629482692000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["A review of public datasets in question answering research"],"prefix":"10.1145","volume":"54","author":[{"given":"B. Barla","family":"Cambazoglu","sequence":"first","affiliation":[{"name":"RMIT University"}]},{"given":"Mark","family":"Sanderson","sequence":"additional","affiliation":[{"name":"RMIT University"}]},{"given":"Falk","family":"Scholer","sequence":"additional","affiliation":[{"name":"RMIT University"}]},{"given":"Bruce","family":"Croft","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst"}]}],"member":"320","published-online":{"date-parts":[[2021,8,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"e_1_2_1_2_1","volume-title":"Embracing data abundance: Booktest dataset for reading comprehension. CoRR, abs\/1610.00956","author":"Bajgar Ondrej","year":"2016"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the Fifth Italian Conference on Computational Linguistics","volume":"2253","author":"Brunato Dominique","year":"2018"},{"key":"e_1_2_1_4_1","first-page":"5515","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference","author":"Carrino Casimiro Pio","year":"2020"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00317"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970398.2970438"},{"key":"e_1_2_1_8_1","first-page":"1777","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers","author":"Cui Yiming","year":"2016"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1600"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.107"},{"key":"e_1_2_1_11_1","volume-title":"Searchqa: A new q&a dataset augmented with context from a search engine. CoRR, abs\/1704.05179","author":"Dunn Matthew","year":"2017"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58219-7_1"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1346"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45442-5_21"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2605"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969428"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Hill Felix","year":"2016"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_2_1_19_1","volume-title":"8th International Conference on Learning Representations. OpenReview.net","author":"Keysers Daniel","year":"2020"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"e_1_2_1_21_1","volume-title":"RuBQ: A russian dataset for question answering over wikidata. CoRR, abs\/2005.10659","author":"Korablinov Vladislav","year":"2020"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation. European Language Resources Association (ELRA)","author":"Lee Kyungjae","year":"2018"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.653"},{"key":"e_1_2_1_26_1","volume-title":"Korean QA dataset for machine reading comprehension","author":"Lim Seungyoung","year":"2019"},{"key":"e_1_2_1_27_1","series-title":"CEUR Workshop Proceedings","volume-title":"Tarek Richard Besold, Antoine Bordes, Artur S. d'Avila Garcez","author":"Nguyen Tri","year":"2016"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1241"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00266"},{"key":"e_1_2_1_32_1","first-page":"193","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Richardson Matthew","year":"2013"},{"key":"e_1_2_1_33_1","volume-title":"DRCD: a chinese machine reading comprehension dataset. CoRR, abs\/1806.00920","author":"Shao Chih-Chieh","year":"2018"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345577"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1496"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"}],"container-title":["ACM SIGIR Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3483382.3483389","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3483382.3483389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:58Z","timestamp":1750191538000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3483382.3483389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["10.1145\/3483382.3483389"],"URL":"https:\/\/doi.org\/10.1145\/3483382.3483389","relation":{},"ISSN":["0163-5840"],"issn-type":[{"value":"0163-5840","type":"print"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"2021-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}