{"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/natural-language-processing-with-small-feed","title":"Natural Language Processing with Small Feed-Forward Networks","arxiv_id":"1708.00214","date":"2017-08-01","proceeding":"EMNLP 2017 9","authors":["Jan A. Botha","Emily Pitler","Ji Ma","Anton Bakalov","Alex Salcianu","David Weiss","Ryan Mcdonald","Slav Petrov"],"abstract":"We show that small and shallow feed-forward neural networks can achieve near\nstate-of-the-art results on a range of unstructured and structured language\nprocessing tasks while being considerably cheaper in memory and computational\nrequirements than deep recurrent models. Motivated by resource-constrained\nenvironments like mobile phones, we showcase simple techniques for obtaining\nsuch small neural network models, and investigate different tradeoffs when\ndeciding how to allocate a small memory budget.","url_abs":"http://arxiv.org/abs/1708.00214v1","url_pdf":"http://arxiv.org/pdf/1708.00214v1.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":"natural-language-processing-with-small-feed","repo_url":"https://github.com/bzz/LangID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.00214","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}