{"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/text-normalization-using-memory-augmented","title":"Text normalization using memory augmented neural networks","arxiv_id":"1806.00044","date":"2018-05-31","proceeding":null,"authors":["Subhojeet Pramanik","Aman Hussain"],"abstract":"We perform text normalization, i.e. the transformation of words from the\nwritten to the spoken form, using a memory augmented neural network. With the\naddition of dynamic memory access and storage mechanism, we present a neural\narchitecture that will serve as a language-agnostic text normalization system\nwhile avoiding the kind of unacceptable errors made by the LSTM-based recurrent\nneural networks. By successfully reducing the frequency of such mistakes, we\nshow that this novel architecture is indeed a better alternative. Our proposed\nsystem requires significantly lesser amounts of data, training time and compute\nresources. Additionally, we perform data up-sampling, circumventing the data\nsparsity problem in some semiotic classes, to show that sufficient examples in\nany particular class can improve the performance of our text normalization\nsystem. Although a few occurrences of these errors still remain in certain\nsemiotic classes, we demonstrate that memory augmented networks with\nmeta-learning capabilities can open many doors to a superior text normalization\nsystem.","url_abs":"http://arxiv.org/abs/1806.00044v3","url_pdf":"http://arxiv.org/pdf/1806.00044v3.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":"text-normalization-using-memory-augmented","repo_url":"https://github.com/cognibit/Text-Normalization-Demo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"text-normalization","task_name":"Text Normalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.00044","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}