{"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/domain-adapted-word-embeddings-for-improved","title":"Domain Adapted Word Embeddings for Improved Sentiment Classification","arxiv_id":"1805.04576","date":"2018-05-11","proceeding":"ACL 2018 7","authors":["Prathusha K Sarma","YIngyu Liang","William A. Sethares"],"abstract":"Generic word embeddings are trained on large-scale generic corpora; Domain\nSpecific (DS) word embeddings are trained only on data from a domain of\ninterest. This paper proposes a method to combine the breadth of generic\nembeddings with the specificity of domain specific embeddings. The resulting\nembeddings, called Domain Adapted (DA) word embeddings, are formed by aligning\ncorresponding word vectors using Canonical Correlation Analysis (CCA) or the\nrelated nonlinear Kernel CCA. Evaluation results on sentiment classification\ntasks show that the DA embeddings substantially outperform both generic and DS\nembeddings when used as input features to standard or state-of-the-art sentence\nencoding algorithms for classification.","url_abs":"http://arxiv.org/abs/1805.04576v1","url_pdf":"http://arxiv.org/pdf/1805.04576v1.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":"domain-adapted-word-embeddings-for-improved","repo_url":"https://github.com/GallupGovt/multivac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"specificity","task_name":"Specificity"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04576","atlas_url":"https://app.syntology.ai/?focus=1805.04576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}