{"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-understanding-from-scratch","title":"Text Understanding from Scratch","arxiv_id":"1502.01710","date":"2015-02-05","proceeding":null,"authors":["Xiang Zhang","Yann Lecun"],"abstract":"This article demontrates that we can apply deep learning to text\nunderstanding from character-level inputs all the way up to abstract text\nconcepts, using temporal convolutional networks (ConvNets). We apply ConvNets\nto various large-scale datasets, including ontology classification, sentiment\nanalysis, and text categorization. We show that temporal ConvNets can achieve\nastonishing performance without the knowledge of words, phrases, sentences and\nany other syntactic or semantic structures with regards to a human language.\nEvidence shows that our models can work for both English and Chinese.","url_abs":"http://arxiv.org/abs/1502.01710v5","url_pdf":"http://arxiv.org/pdf/1502.01710v5.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-understanding-from-scratch","repo_url":"https://github.com/sunginmkone/AWS_Training_NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"text-understanding-from-scratch","repo_url":"https://github.com/zhangxiangxiao/Crepe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.01710","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}