{"url":"/method/par-transformer","slug":"par-transformer","name":"PAR Transformer","full_name":"PAR Transformer","full_name_withheld":false,"description_markdown":"**PAR Transformer** is a [Transformer](https://paperswithcode.com/methods/category/transformers) model that uses 63% fewer [self-attention blocks](https://paperswithcode.com/method/scaled), replacing them with [feed-forward blocks](https://paperswithcode.com/method/position-wise-feed-forward-layer), while retaining test accuracies. It is based on the [Transformer-XL](https://paperswithcode.com/method/transformer-xl) architecture and uses [neural architecture search](https://paperswithcode.com/task/architecture-search) to find an an efficient pattern of blocks in the transformer architecture.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pay Attention when Required","paper":"/paper/pay-attention-when-required","first_author":"Swetha Mandava","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pay-attention-when-required"},"source":{"url":"https://arxiv.org/abs/2009.04534v3","title":"Pay Attention when Required","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":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","n_code_links":2,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/paraphrase-identification","name":"Paraphrase Identification","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1}],"tasks_shown":4,"n_tasks":4,"usage_by_year":[{"year":"2020","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/par-transformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}