{"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/robust-and-scalable-differentiable-neural","title":"Robust and Scalable Differentiable Neural Computer for Question Answering","arxiv_id":"1807.02658","date":"2018-07-07","proceeding":"WS 2018 7","authors":["Jörg Franke","Jan Niehues","Alex Waibel"],"abstract":"Deep learning models are often not easily adaptable to new tasks and require\ntask-specific adjustments. The differentiable neural computer (DNC), a\nmemory-augmented neural network, is designed as a general problem solver which\ncan be used in a wide range of tasks. But in reality, it is hard to apply this\nmodel to new tasks. We analyze the DNC and identify possible improvements\nwithin the application of question answering. This motivates a more robust and\nscalable DNC (rsDNC). The objective precondition is to keep the general\ncharacter of this model intact while making its application more reliable and\nspeeding up its required training time. The rsDNC is distinguished by a more\nrobust training, a slim memory unit and a bidirectional architecture. We not\nonly achieve new state-of-the-art performance on the bAbI task, but also\nminimize the performance variance between different initializations.\nFurthermore, we demonstrate the simplified applicability of the rsDNC to new\ntasks with passable results on the CNN RC task without adaptions.","url_abs":"http://arxiv.org/abs/1807.02658v1","url_pdf":"http://arxiv.org/pdf/1807.02658v1.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":"robust-and-scalable-differentiable-neural","repo_url":"https://github.com/joergfranke/ADNC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}