{"url":"/method/strata","slug":"strata","name":"STraTA","full_name":"Self-Training with Task Augmentation","full_name_withheld":false,"description_markdown":"**STraTA**, or **Self-Training with Task Augmentation**, is a self-training approach that builds on two key ideas for effective leverage of unlabeled data. First, STraTA uses task augmentation, a technique that synthesizes a large amount of data for auxiliary-task fine-tuning from target-task unlabeling texts. Second, STRATA performs self-training by further fine-tuning the strong base model created by task augmentation on a broad distribution of pseudo-labeled data.\r\n\r\nIn task augmentation, we train an NLI data generation model and use it to synthesize a large amount of in-domain NLI training data for each given target task, which is then used for auxiliary (intermediate) fine-tuning. The self-training algorithm iteratively learns a better model using a concatenation of labeled and pseudo-labeled examples. At each iteration, we always start with the auxiliary-task model produced by task augmentation and train on a broad distribution of pseudo-labeled data.","description_state":"present","introduced_year":null,"introduced_by":{"title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","paper":"/paper/strata-self-training-with-task-augmentation","first_author":"Tu Vu","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/strata-self-training-with-task-augmentation"},"source":{"url":"https://arxiv.org/abs/2109.06270v2","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Self-Training Methods","url":"/methods/category/self-training-methods","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Semi-Supervised Learning Methods","url":"/methods/category/semi-supervised-learning-methods","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/strata-self-training-with-task-augmentation","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","date":"2021-09-13","arxiv_id":"2109.06270","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":"/task/few-shot-nli","name":"Few-Shot NLI","papers":1},{"task":null,"name":"SST-2","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/strata"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}