{"url":"/method/mt-pet","slug":"mt-pet","name":"MT-PET","full_name":"MT-PET","full_name_withheld":false,"description_markdown":"**MT-PET** is a multi-task version of [Pattern Exploiting Training](https://arxiv.org/abs/2001.07676) (PET) for exaggeration detection, which leverages knowledge from complementary cloze-style QA tasks to improve few-shot learning. It defines pairs of complementary pattern-verbalizer pairs for a main task and auxiliary task. These PVPs are then used to train PET on data from both tasks.\r\n\r\nPET uses the masked language modeling objective of pretrained language models to transform a task into one or more cloze-style question answering tasks.  In the original PET implementation, PVPs are defined for a single target task. MT-PET extends this by allowing for auxiliary PVPs from related tasks, adding complementary cloze-style QA tasks during training. The motivation for the multi-task approach is two-fold: 1) complementary cloze-style tasks can potentially help the model to learn different aspects of the main task, i.e. the similar tasks of exaggeration detection and claim strength prediction; 2) data on related tasks can be utilized during training, which is important in situations where data for the main task is limited.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Semi-Supervised Exaggeration Detection of Health Science Press Releases","paper":"/paper/semi-supervised-exaggeration-detection-of","first_author":"Dustin Wright","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/semi-supervised-exaggeration-detection-of"},"source":{"url":"https://arxiv.org/abs/2108.13493v1","title":"Semi-Supervised Exaggeration Detection of Health Science Press Releases","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Exaggeration Detection Models","url":"/methods/category/exaggeration-detection-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/semi-supervised-exaggeration-detection-of","title":"Semi-Supervised Exaggeration Detection of Health Science Press Releases","date":"2021-08-30","arxiv_id":"2108.13493","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/articles","name":"Articles","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","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/mt-pet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}