{"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/learning-robust-representations-of-text","title":"Learning Robust Representations of Text","arxiv_id":"1609.06082","date":"2016-09-20","proceeding":"EMNLP 2016 11","authors":["Yitong Li","Trevor Cohn","Timothy Baldwin"],"abstract":"Deep neural networks have achieved remarkable results across many language\nprocessing tasks, however these methods are highly sensitive to noise and\nadversarial attacks. We present a regularization based method for limiting\nnetwork sensitivity to its inputs, inspired by ideas from computer vision, thus\nlearning models that are more robust. Empirical evaluation over a range of\nsentiment datasets with a convolutional neural network shows that, compared to\na baseline model and the dropout method, our method achieves superior\nperformance over noisy inputs and out-of-domain data.","url_abs":"http://arxiv.org/abs/1609.06082v1","url_pdf":"http://arxiv.org/pdf/1609.06082v1.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":"learning-robust-representations-of-text","repo_url":"https://github.com/lrank/Robust-Representation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.06082","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}