{"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/whats-in-a-domain-learning-domain-robust-text","title":"What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training","arxiv_id":"1805.06088","date":"2018-05-16","proceeding":"NAACL 2018 6","authors":["Yitong Li","Timothy Baldwin","Trevor Cohn"],"abstract":"Most real world language problems require learning from heterogenous corpora,\nraising the problem of learning robust models which generalise well to both\nsimilar (in domain) and dissimilar (out of domain) instances to those seen in\ntraining. This requires learning an underlying task, while not learning\nirrelevant signals and biases specific to individual domains. We propose a\nnovel method to optimise both in- and out-of-domain accuracy based on joint\nlearning of a structured neural model with domain-specific and domain-general\ncomponents, coupled with adversarial training for domain. Evaluating on\nmulti-domain language identification and multi-domain sentiment analysis, we\nshow substantial improvements over standard domain adaptation techniques, and\ndomain-adversarial training.","url_abs":"http://arxiv.org/abs/1805.06088v1","url_pdf":"http://arxiv.org/pdf/1805.06088v1.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":"whats-in-a-domain-learning-domain-robust-text","repo_url":"https://github.com/lrank/Domain_Robust_Text_Representation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.06088","atlas_url":"https://app.syntology.ai/?focus=1805.06088","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}