{"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/mixtext-linguistically-informed-interpolation","title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification","arxiv_id":"2004.12239","date":"2020-04-25","proceeding":"ACL 2020 6","authors":["Jiaao Chen","Zichao Yang","Diyi Yang"],"abstract":"This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks. The improvement is especially prominent when supervision is extremely limited. We have publicly released our code at https://github.com/GT-SALT/MixText.","url_abs":"https://arxiv.org/abs/2004.12239v1","url_pdf":"https://arxiv.org/pdf/2004.12239v1.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":"mixtext-linguistically-informed-interpolation","repo_url":"https://github.com/GT-SALT/MixText","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"mixtext-linguistically-informed-interpolation","repo_url":"https://github.com/clovaai/vat-d","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":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"semi-supervised-text-classification-1","task_name":"Semi-Supervised Text Classification"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"mixtext","method_name":"MixText"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mixtext","name":"MixText","full_name":"MixText"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.12239","atlas_url":"https://app.syntology.ai/?focus=2004.12239","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}