{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/triviaqa-a-large-scale-distantly-supervised","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","arxiv_id":"1705.03551","date":"2017-05-09","proceeding":"ACL 2017 7","authors":["Mandar Joshi","Eunsol Choi","Daniel S. Weld","Luke Zettlemoyer"],"abstract":"We present TriviaQA, a challenging reading comprehension dataset containing\nover 650K question-answer-evidence triples. TriviaQA includes 95K\nquestion-answer pairs authored by trivia enthusiasts and independently gathered\nevidence documents, six per question on average, that provide high quality\ndistant supervision for answering the questions. We show that, in comparison to\nother recently introduced large-scale datasets, TriviaQA (1) has relatively\ncomplex, compositional questions, (2) has considerable syntactic and lexical\nvariability between questions and corresponding answer-evidence sentences, and\n(3) requires more cross sentence reasoning to find answers. We also present two\nbaseline algorithms: a feature-based classifier and a state-of-the-art neural\nnetwork, that performs well on SQuAD reading comprehension. Neither approach\ncomes close to human performance (23% and 40% vs. 80%), suggesting that\nTriviaQA is a challenging testbed that is worth significant future study. Data\nand code available at -- http://nlp.cs.washington.edu/triviaqa/","url_abs":"http://arxiv.org/abs/1705.03551v2","url_pdf":"http://arxiv.org/pdf/1705.03551v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"triviaqa-a-large-scale-distantly-supervised","repo_url":"https://github.com/chrisc36/debias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"triviaqa-a-large-scale-distantly-supervised","repo_url":"https://github.com/hyintell/retrievalqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"triviaqa-a-large-scale-distantly-supervised","repo_url":"https://github.com/mandarjoshi90/triviaqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[{"slug":"triviaqa","name":"TriviaQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.03551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03551"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hyintell/retrievalqa","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mandarjoshi90/triviaqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chrisc36/debias","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran_violates":1,"ran_honours":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"147e0ae162d88334","entry":"add_triple_data","repo":"mandarjoshi90/triviaqa","repo_kind":"listed","path":"utils/convert_to_squad_format.py","file_url":"https://github.com/mandarjoshi90/triviaqa/blob/HEAD/utils/convert_to_squad_format.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"147e0ae162d88334"}},{"code_sha256_prefix":"2c66ac5f9374f1f7","entry":"exact_match_score","repo":"mandarjoshi90/triviaqa","repo_kind":"listed","path":"evaluation/triviaqa_evaluation.py","file_url":"https://github.com/mandarjoshi90/triviaqa/blob/HEAD/evaluation/triviaqa_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c66ac5f9374f1f7"}},{"code_sha256_prefix":"5d0a37a7c59decf8","entry":"f1_score","repo":"mandarjoshi90/triviaqa","repo_kind":"listed","path":"evaluation/triviaqa_evaluation.py","file_url":"https://github.com/mandarjoshi90/triviaqa/blob/HEAD/evaluation/triviaqa_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d0a37a7c59decf8"}},{"code_sha256_prefix":"2879260bc19381c8","entry":"normalize_answer","repo":"mandarjoshi90/triviaqa","repo_kind":"listed","path":"evaluation/triviaqa_evaluation.py","file_url":"https://github.com/mandarjoshi90/triviaqa/blob/HEAD/evaluation/triviaqa_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2879260bc19381c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}