{"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/inducing-regular-grammars-using-recurrent","title":"Inducing Regular Grammars Using Recurrent Neural Networks","arxiv_id":"1710.10453","date":"2017-10-28","proceeding":null,"authors":["Mor Cohen","Avi Caciularu","Idan Rejwan","Jonathan Berant"],"abstract":"Grammar induction is the task of learning a grammar from a set of examples.\nRecently, neural networks have been shown to be powerful learning machines that\ncan identify patterns in streams of data. In this work we investigate their\neffectiveness in inducing a regular grammar from data, without any assumptions\nabout the grammar. We train a recurrent neural network to distinguish between\nstrings that are in or outside a regular language, and utilize an algorithm for\nextracting the learned finite-state automaton. We apply this method to several\nregular languages and find unexpected results regarding the connections between\nthe network's states that may be regarded as evidence for generalization.","url_abs":"http://arxiv.org/abs/1710.10453v2","url_pdf":"http://arxiv.org/pdf/1710.10453v2.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":"inducing-regular-grammars-using-recurrent","repo_url":"https://github.com/acrola/RnnInduceRegularGrammar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}