{"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/large-scale-simple-question-answering-with","title":"Large-scale Simple Question Answering with Memory Networks","arxiv_id":"1506.02075","date":"2015-06-05","proceeding":null,"authors":["Antoine Bordes","Nicolas Usunier","Sumit Chopra","Jason Weston"],"abstract":"Training large-scale question answering systems is complicated because\ntraining sources usually cover a small portion of the range of possible\nquestions. This paper studies the impact of multitask and transfer learning for\nsimple question answering; a setting for which the reasoning required to answer\nis quite easy, as long as one can retrieve the correct evidence given a\nquestion, which can be difficult in large-scale conditions. To this end, we\nintroduce a new dataset of 100k questions that we use in conjunction with\nexisting benchmarks. We conduct our study within the framework of Memory\nNetworks (Weston et al., 2015) because this perspective allows us to eventually\nscale up to more complex reasoning, and show that Memory Networks can be\nsuccessfully trained to achieve excellent performance.","url_abs":"http://arxiv.org/abs/1506.02075v1","url_pdf":"http://arxiv.org/pdf/1506.02075v1.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":"large-scale-simple-question-answering-with","repo_url":"https://github.com/au1khan/FactQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"large-scale-simple-question-answering-with","repo_url":"https://github.com/aukhanee/FactQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"large-scale-simple-question-answering-with","repo_url":"https://github.com/facebookresearch/ParlAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"simplequestions","name":"SimpleQuestions","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-reverb","task":"Question Answering","dataset":"Reverb","model":"Memory Networks (ensemble)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"68%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-simplequestions","task":"Question Answering","dataset":"SimpleQuestions","model":"Memory Networks (ensemble)","rank_in_archive_order":1,"of":1,"metrics":{"F1":"63.9%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-webquestions","task":"Question Answering","dataset":"WebQuestions","model":"Memory Networks (ensemble)","rank_in_archive_order":35,"of":37,"metrics":{"F1":"42.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02075","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}