{"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/projecting-embeddings-for-domain-adaptation","title":"Projecting Embeddings for Domain Adaptation: Joint Modeling of Sentiment Analysis in Diverse Domains","arxiv_id":"1806.04381","date":"2018-06-12","proceeding":null,"authors":["Jeremy Barnes","Roman Klinger","Sabine Schulte im Walde"],"abstract":"Domain adaptation for sentiment analysis is challenging due to the fact that\nsupervised classifiers are very sensitive to changes in domain. The two most\nprominent approaches to this problem are structural correspondence learning and\nautoencoders. However, they either require long training times or suffer\ngreatly on highly divergent domains. Inspired by recent advances in\ncross-lingual sentiment analysis, we provide a novel perspective and cast the\ndomain adaptation problem as an embedding projection task. Our model takes as\ninput two mono-domain embedding spaces and learns to project them to a\nbi-domain space, which is jointly optimized to (1) project across domains and\nto (2) predict sentiment. We perform domain adaptation experiments on 20\nsource-target domain pairs for sentiment classification and report novel\nstate-of-the-art results on 11 domain pairs, including the Amazon domain\nadaptation datasets and SemEval 2013 and 2016 datasets. Our analysis shows that\nour model performs comparably to state-of-the-art approaches on domains that\nare similar, while performing significantly better on highly divergent domains.\nOur code is available at https://github.com/jbarnesspain/domain_blse","url_abs":"http://arxiv.org/abs/1806.04381v2","url_pdf":"http://arxiv.org/pdf/1806.04381v2.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":"projecting-embeddings-for-domain-adaptation","repo_url":"https://github.com/jbarnesspain/domain_blse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"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=1806.04381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}