{"url":"/method/squeezebert","slug":"squeezebert","name":"SqueezeBERT","full_name":"SqueezeBERT","full_name_withheld":false,"description_markdown":"**SqueezeBERT** is an efficient architectural variant of [BERT](https://paperswithcode.com/method/bert) for natural language processing that uses [grouped convolutions](https://paperswithcode.com/method/grouped-convolution). It is much like BERT-base, but with positional feedforward connection layers implemented as convolutions, and grouped [convolution](https://paperswithcode.com/method/convolution) for many of the layers.","description_state":"present","introduced_year":null,"introduced_by":{"title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","paper":"/paper/squeezebert-what-can-computer-vision-teach","first_author":"Forrest N. Iandola","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/squeezebert-what-can-computer-vision-teach"},"source":{"url":"https://arxiv.org/abs/2006.11316v1","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","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":"Autoencoding Transformers","url":"/methods/category/autoencoding-transformers","pwc_aliases":[]},{"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/squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","n_code_links":6,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}}],"papers_shown":1,"tasks":[{"task":"/task/linguistic-acceptability","name":"Linguistic Acceptability","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/text-classification","name":"Text Classification","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1}],"tasks_shown":7,"n_tasks":7,"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/squeezebert"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}