{"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/adaptive-semi-supervised-learning-for-cross","title":"Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification","arxiv_id":"1809.00530","date":"2018-09-03","proceeding":"EMNLP 2018 10","authors":["Ruidan He","Wee Sun Lee","Hwee Tou Ng","Daniel Dahlmeier"],"abstract":"We consider the cross-domain sentiment classification problem, where a\nsentiment classifier is to be learned from a source domain and to be\ngeneralized to a target domain. Our approach explicitly minimizes the distance\nbetween the source and the target instances in an embedded feature space. With\nthe difference between source and target minimized, we then exploit additional\ninformation from the target domain by consolidating the idea of semi-supervised\nlearning, for which, we jointly employ two regularizations -- entropy\nminimization and self-ensemble bootstrapping -- to incorporate the unlabeled\ntarget data for classifier refinement. Our experimental results demonstrate\nthat the proposed approach can better leverage unlabeled data from the target\ndomain and achieve substantial improvements over baseline methods in various\nexperimental settings.","url_abs":"http://arxiv.org/abs/1809.00530v1","url_pdf":"http://arxiv.org/pdf/1809.00530v1.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":"adaptive-semi-supervised-learning-for-cross","repo_url":"https://github.com/ruidan/DAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00530","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}