{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1506.02516","atlas_url":"https://app.syntology.ai/?focus=1506.02516","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1506.02516"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1506.02516\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1506.02516"},"call":"get_concepts_for_paper(arxiv_id=\"1506.02516\")"}],"by_repo":[{"repo":"TIANHAO-WANG/nnstack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cflamant/neural-stack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"viking-sudo-rm/StackNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tensorflow/tensor2tensor","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["1803.07416","1903.00374","2005.11197"],"harvested_for_calls":[{"arxiv_id":"1803.07416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.07416"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.07416\")"},{"arxiv_id":"1903.00374","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1903.00374"},"call":"get_harvested_code_for_paper(arxiv_id=\"1903.00374\")"},{"arxiv_id":"2005.11197","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.11197"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.11197\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"01b5cd8641f983f9c3cd2f2e46c64530fd26bfff8452fbc5a19b2ace2da5f012","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}