{"url":"/dataset/simplequestions","name":"SimpleQuestions","full_name":null,"description_markdown":"**SimpleQuestions** is a large-scale factoid question answering dataset. It consists of 108,442 natural language questions, each paired with a corresponding fact from Freebase knowledge base. Each fact is a triple (subject, relation, object) and the answer to the question is always the object. The dataset is divided into training, validation, and test  sets with 75,910, 10,845 and 21,687 questions respectively.\r\n\r\nSource: [Hierarchical Memory Networks](https://arxiv.org/abs/1605.07427)\r\nImage Source: [https://paperswithcode.com/paper/large-scale-simple-question-answering-with/](https://paperswithcode.com/paper/large-scale-simple-question-answering-with/)","description_withheld":null,"homepage":"https://github.com/davidgolub/SimpleQA/tree/master/datasets/SimpleQuestions","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-simple-question-answering-with","title":"Large-scale Simple Question Answering with Memory Networks","first_author":"Antoine Bordes","url":null},"license":{"name":"BSD-3-Clause License","url":"https://github.com/davidgolub/SimpleQA/blob/master/license.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SimpleQuestions"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fbougares/simple_questions_v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/simple_questions_v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#simple-questions","frameworks":["pytorch"]},{"repo":"https://github.com/davidgolub/SimpleQA","url":"https://github.com/davidgolub/SimpleQA","frameworks":[]}],"num_papers_in_archive":120,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/knowledge-base-question-answering-on-2","task":"Knowledge Base Question Answering","dataset_variant":"SimpleQuestions","rows":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"PoG-GPT4 (Tan et al., 2024)","paper":"/paper/paths-over-graph-knowledge-graph-enpowered","metrics":{"EM":"84"},"code_links":[{"title":"SteveTANTAN/PoG","url":"https://github.com/SteveTANTAN/PoG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-simplequestions","task":"Question Answering","dataset_variant":"SimpleQuestions","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"Memory Networks (ensemble)","paper":"/paper/large-scale-simple-question-answering-with","metrics":{"F1":"63.9%"},"code_links":[{"title":"facebookresearch/ParlAI","url":"https://github.com/facebookresearch/ParlAI"},{"title":"au1khan/FactQA","url":"https://github.com/au1khan/FactQA"},{"title":"aukhanee/FactQA","url":"https://github.com/aukhanee/FactQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/large-scale-simple-question-answering-with","title":"Large-scale Simple Question Answering with Memory Networks","date":"2015-06-05","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}