{"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/neural-based-noise-filtering-from-word","title":"Neural-based Noise Filtering from Word Embeddings","arxiv_id":"1610.01874","date":"2016-10-06","proceeding":"COLING 2016 12","authors":["Kim Anh Nguyen","Sabine Schulte im Walde","Ngoc Thang Vu"],"abstract":"Word embeddings have been demonstrated to benefit NLP tasks impressively.\nYet, there is room for improvement in the vector representations, because\ncurrent word embeddings typically contain unnecessary information, i.e., noise.\nWe propose two novel models to improve word embeddings by unsupervised\nlearning, in order to yield word denoising embeddings. The word denoising\nembeddings are obtained by strengthening salient information and weakening\nnoise in the original word embeddings, based on a deep feed-forward neural\nnetwork filter. Results from benchmark tasks show that the filtered word\ndenoising embeddings outperform the original word embeddings.","url_abs":"http://arxiv.org/abs/1610.01874v1","url_pdf":"http://arxiv.org/pdf/1610.01874v1.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":"neural-based-noise-filtering-from-word","repo_url":"https://github.com/nguyenkh/NeuralDenoising","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}