{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rosita-refined-bert-compression-with","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","arxiv_id":"2103.11367","date":"2021-03-21","proceeding":null,"authors":["Yuanxin Liu","Zheng Lin","Fengcheng Yuan"],"abstract":"Pre-trained language models of the BERT family have defined the state-of-the-arts in a wide range of NLP tasks. However, the performance of BERT-based models is mainly driven by the enormous amount of parameters, which hinders their application to resource-limited scenarios. Faced with this problem, recent studies have been attempting to compress BERT into a small-scale model. However, most previous work primarily focuses on a single kind of compression technique, and few attention has been paid to the combination of different methods. When BERT is compressed with integrated techniques, a critical question is how to design the entire compression framework to obtain the optimal performance. In response to this question, we integrate three kinds of compression methods (weight pruning, low-rank factorization and knowledge distillation (KD)) and explore a range of designs concerning model architecture, KD strategy, pruning frequency and learning rate schedule. We find that a careful choice of the designs is crucial to the performance of the compressed model. Based on the empirical findings, our best compressed model, dubbed Refined BERT cOmpreSsion with InTegrAted techniques (ROSITA), is $7.5 \\times$ smaller than BERT while maintains $98.5\\%$ of the performance on five tasks of the GLUE benchmark, outperforming the previous BERT compression methods with similar parameter budget. The code is available at https://github.com/llyx97/Rosita.","url_abs":"https://arxiv.org/abs/2103.11367v1","url_pdf":"https://arxiv.org/pdf/2103.11367v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rosita-refined-bert-compression-with","repo_url":"https://github.com/llyx97/Rosita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.11367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11367"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/llyx97/Rosita","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"be8a3de43df17b34","entry":"HeadAttention","repo":"llyx97/Rosita","repo_kind":"official","path":"Pruning/transformer/modeling_prun.py","file_url":"https://github.com/llyx97/Rosita/blob/HEAD/Pruning/transformer/modeling_prun.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be8a3de43df17b34"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}