{"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/a-fixed-size-encoding-method-for-variable","title":"A Fixed-Size Encoding Method for Variable-Length Sequences with its Application to Neural Network Language Models","arxiv_id":"1505.01504","date":"2015-05-06","proceeding":null,"authors":["Shiliang Zhang","Hui Jiang","MingBin Xu","JunFeng Hou","Li-Rong Dai"],"abstract":"In this paper, we propose the new fixed-size ordinally-forgetting encoding\n(FOFE) method, which can almost uniquely encode any variable-length sequence of\nwords into a fixed-size representation. FOFE can model the word order in a\nsequence using a simple ordinally-forgetting mechanism according to the\npositions of words. In this work, we have applied FOFE to feedforward neural\nnetwork language models (FNN-LMs). Experimental results have shown that without\nusing any recurrent feedbacks, FOFE based FNN-LMs can significantly outperform\nnot only the standard fixed-input FNN-LMs but also the popular RNN-LMs.","url_abs":"http://arxiv.org/abs/1505.01504v2","url_pdf":"http://arxiv.org/pdf/1505.01504v2.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":"a-fixed-size-encoding-method-for-variable","repo_url":"https://github.com/SourangshuGhosh/Bag-of-words-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}