{"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/parallelizable-stack-long-short-term-memory","title":"Parallelizable Stack Long Short-Term Memory","arxiv_id":"1904.03409","date":"2019-04-06","proceeding":"WS 2019 6","authors":["Shuoyang Ding","Philipp Koehn"],"abstract":"Stack Long Short-Term Memory (StackLSTM) is useful for various applications\nsuch as parsing and string-to-tree neural machine translation, but it is also\nknown to be notoriously difficult to parallelize for GPU training due to the\nfact that the computations are dependent on discrete operations. In this paper,\nwe tackle this problem by utilizing state access patterns of StackLSTM to\nhomogenize computations with regard to different discrete operations. Our\nparsing experiments show that the method scales up almost linearly with\nincreasing batch size, and our parallelized PyTorch implementation trains\nsignificantly faster compared to the Dynet C++ implementation.","url_abs":"http://arxiv.org/abs/1904.03409v1","url_pdf":"http://arxiv.org/pdf/1904.03409v1.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":"parallelizable-stack-long-short-term-memory","repo_url":"https://github.com/shuoyangd/hoolock","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03409","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}