{"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/context-free-transductions-with-neural-stacks","title":"Context-Free Transductions with Neural Stacks","arxiv_id":"1809.02836","date":"2018-09-08","proceeding":"WS 2018 11","authors":["Yiding Hao","William Merrill","Dana Angluin","Robert Frank","Noah Amsel","Andrew Benz","Simon Mendelsohn"],"abstract":"This paper analyzes the behavior of stack-augmented recurrent neural network\n(RNN) models. Due to the architectural similarity between stack RNNs and\npushdown transducers, we train stack RNN models on a number of tasks, including\nstring reversal, context-free language modelling, and cumulative XOR\nevaluation. Examining the behavior of our networks, we show that\nstack-augmented RNNs can discover intuitive stack-based strategies for solving\nour tasks. However, stack RNNs are more difficult to train than classical\narchitectures such as LSTMs. Rather than employ stack-based strategies, more\ncomplex networks often find approximate solutions by using the stack as\nunstructured memory.","url_abs":"http://arxiv.org/abs/1809.02836v1","url_pdf":"http://arxiv.org/pdf/1809.02836v1.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":"context-free-transductions-with-neural-stacks","repo_url":"https://github.com/viking-sudo-rm/StackNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"context-free-transductions-with-neural-stacks","repo_url":"https://github.com/suzgunmirac/marnns","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.02836","atlas_url":"https://app.syntology.ai/?focus=1809.02836","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}