{"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/recurrent-memory-networks-for-language","title":"Recurrent Memory Networks for Language Modeling","arxiv_id":"1601.01272","date":"2016-01-06","proceeding":"NAACL 2016 6","authors":["Ke Tran","Arianna Bisazza","Christof Monz"],"abstract":"Recurrent Neural Networks (RNN) have obtained excellent result in many\nnatural language processing (NLP) tasks. However, understanding and\ninterpreting the source of this success remains a challenge. In this paper, we\npropose Recurrent Memory Network (RMN), a novel RNN architecture, that not only\namplifies the power of RNN but also facilitates our understanding of its\ninternal functioning and allows us to discover underlying patterns in data. We\ndemonstrate the power of RMN on language modeling and sentence completion\ntasks. On language modeling, RMN outperforms Long Short-Term Memory (LSTM)\nnetwork on three large German, Italian, and English dataset. Additionally we\nperform in-depth analysis of various linguistic dimensions that RMN captures.\nOn Sentence Completion Challenge, for which it is essential to capture sentence\ncoherence, our RMN obtains 69.2% accuracy, surpassing the previous\nstate-of-the-art by a large margin.","url_abs":"http://arxiv.org/abs/1601.01272v2","url_pdf":"http://arxiv.org/pdf/1601.01272v2.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":"recurrent-memory-networks-for-language","repo_url":"https://github.com/ketranm/RMN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":null},{"paper_slug":"recurrent-memory-networks-for-language","repo_url":"https://github.com/simonjisu/NMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-completion","task_name":"Sentence Completion"}],"methods":[{"method_slug":"memory-network","method_name":"Memory Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}