{"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/learning-to-transduce-with-unbounded-memory","title":"Learning to Transduce with Unbounded Memory","arxiv_id":"1506.02516","date":"2015-06-08","proceeding":"NeurIPS 2015 12","authors":["Edward Grefenstette","Karl Moritz Hermann","Mustafa Suleyman","Phil Blunsom"],"abstract":"Recently, strong results have been demonstrated by Deep Recurrent Neural\nNetworks on natural language transduction problems. In this paper we explore\nthe representational power of these models using synthetic grammars designed to\nexhibit phenomena similar to those found in real transduction problems such as\nmachine translation. These experiments lead us to propose new memory-based\nrecurrent networks that implement continuously differentiable analogues of\ntraditional data structures such as Stacks, Queues, and DeQues. We show that\nthese architectures exhibit superior generalisation performance to Deep RNNs\nand are often able to learn the underlying generating algorithms in our\ntransduction experiments.","url_abs":"http://arxiv.org/abs/1506.02516v3","url_pdf":"http://arxiv.org/pdf/1506.02516v3.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":"learning-to-transduce-with-unbounded-memory","repo_url":"https://github.com/TIANHAO-WANG/nnstack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-transduce-with-unbounded-memory","repo_url":"https://github.com/cflamant/neural-stack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-transduce-with-unbounded-memory","repo_url":"https://github.com/viking-sudo-rm/StackNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-transduce-with-unbounded-memory","repo_url":"https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/research/neural_stack.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"natural-language-transduction","task_name":"Natural Language Transduction"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02516","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}