{"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/word-embedding-perturbation-for-sentence","title":"Word Embedding Perturbation for Sentence Classification","arxiv_id":"1804.08166","date":"2018-04-22","proceeding":null,"authors":["Dongxu Zhang","Zhichao Yang"],"abstract":"In this technique report, we aim to mitigate the overfitting problem of\nnatural language by applying data augmentation methods. Specifically, we\nattempt several types of noise to perturb the input word embedding, such as\nGaussian noise, Bernoulli noise, and adversarial noise, etc. We also apply\nseveral constraints on different types of noise. By implementing these proposed\ndata augmentation methods, the baseline models can gain improvements on several\nsentence classification tasks.","url_abs":"http://arxiv.org/abs/1804.08166v1","url_pdf":"http://arxiv.org/pdf/1804.08166v1.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":"word-embedding-perturbation-for-sentence","repo_url":"https://github.com/zhangdongxu/word-embedding-perturbation","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.08166","atlas_url":"https://app.syntology.ai/?focus=1804.08166","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}