{"url":"/method/bort","slug":"bort","name":"Bort","full_name":"Bort","full_name_withheld":false,"description_markdown":"**Bort** is a parametric architectural variant of the [BERT](https://paperswithcode.com/method/bert) architecture. It extracts an optimal subset of architectural parameters for the BERT architecture through a [neural architecture search](https://paperswithcode.com/method/neural-architecture-search) approach; in particular, a fully polynomial-time approximation scheme (FPTAS). This optimal subset - “Bort” - is demonstrably smaller, having an effective size of $5.5 \\%$ the original BERT-large architecture, and $16\\%$ of the net size. Bort is also able to be pretrained in $288$ GPU hours, which is $1.2\\%$ less than the time required to pretrain the highest-performing BERT parametric architecture variant, RoBERTa-large ([RoBERTa](https://paperswithcode.com/method/roberta)), and about $33\\%","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2010.10499v2","title":"Optimal Subarchitecture Extraction For BERT","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":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/bort-towards-explainable-neural-networks-with","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","date":"2022-12-18","arxiv_id":"2212.09062","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":"/paper/bort-back-and-denoising-reconstruction-for-1","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2022-05-05","arxiv_id":"2205.02471","n_code_links":1,"syntology":null},{"paper":null,"title":"RobBERTje: a Distilled Dutch BERT Model","date":"2022-04-28","arxiv_id":"2204.13511","n_code_links":0,"syntology":null},{"paper":null,"title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/optimal-subarchitecture-extraction-for-bert","title":"Optimal Subarchitecture Extraction For BERT","date":"2020-10-20","arxiv_id":"2010.10499","n_code_links":3,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/denoising","name":"Denoising","papers":2},{"task":null,"name":"CPU","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/lightweight-deployment","name":"Lightweight Deployment","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1},{"task":"/task/model","name":"model","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bort"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}