{"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/effective-use-of-word-order-for-text-1","title":"Effective Use of Word Order for Text Categorization with Convolutional Neural Networks","arxiv_id":"1412.1058","date":"2014-12-01","proceeding":"HLT 2015 5","authors":["Rie Johnson","Tong Zhang"],"abstract":"Convolutional neural network (CNN) is a neural network that can make use of\nthe internal structure of data such as the 2D structure of image data. This\npaper studies CNN on text categorization to exploit the 1D structure (namely,\nword order) of text data for accurate prediction. Instead of using\nlow-dimensional word vectors as input as is often done, we directly apply CNN\nto high-dimensional text data, which leads to directly learning embedding of\nsmall text regions for use in classification. In addition to a straightforward\nadaptation of CNN from image to text, a simple but new variation which employs\nbag-of-word conversion in the convolution layer is proposed. An extension to\ncombine multiple convolution layers is also explored for higher accuracy. The\nexperiments demonstrate the effectiveness of our approach in comparison with\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1412.1058v2","url_pdf":"http://arxiv.org/pdf/1412.1058v2.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":"effective-use-of-word-order-for-text-1","repo_url":"https://github.com/gmichalo/question_identification_on_medical_logs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"effective-use-of-word-order-for-text-1","repo_url":"https://github.com/jean-kunz/ml_research_papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"effective-use-of-word-order-for-text-1","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"effective-use-of-word-order-for-text-1","repo_url":"https://github.com/tensorflow/models/tree/master/research/sentiment_analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"seq2-bown-CNN","rank_in_archive_order":32,"of":49,"metrics":{"Accuracy":"92.33"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.1058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}