{"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/jack-the-reader-a-machine-reading-framework","title":"Jack the Reader - A Machine Reading Framework","arxiv_id":"1806.08727","date":"2018-06-20","proceeding":null,"authors":["Dirk Weissenborn","Pasquale Minervini","Tim Dettmers","Isabelle Augenstein","Johannes Welbl","Tim Rocktäschel","Matko Bošnjak","Jeff Mitchell","Thomas Demeester","Pontus Stenetorp","Sebastian Riedel"],"abstract":"Many Machine Reading and Natural Language Understanding tasks require reading\nsupporting text in order to answer questions. For example, in Question\nAnswering, the supporting text can be newswire or Wikipedia articles; in\nNatural Language Inference, premises can be seen as the supporting text and\nhypotheses as questions. Providing a set of useful primitives operating in a\nsingle framework of related tasks would allow for expressive modelling, and\neasier model comparison and replication. To that end, we present Jack the\nReader (Jack), a framework for Machine Reading that allows for quick model\nprototyping by component reuse, evaluation of new models on existing datasets\nas well as integrating new datasets and applying them on a growing set of\nimplemented baseline models. Jack is currently supporting (but not limited to)\nthree tasks: Question Answering, Natural Language Inference, and Link\nPrediction. It is developed with the aim of increasing research efficiency and\ncode reuse.","url_abs":"http://arxiv.org/abs/1806.08727v1","url_pdf":"http://arxiv.org/pdf/1806.08727v1.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":"jack-the-reader-a-machine-reading-framework","repo_url":"https://github.com/uclmr/jack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jack-the-reader-a-machine-reading-framework","repo_url":"https://github.com/uclnlp/jack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.08727","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}