{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:27:08Z","timestamp":1781018828012,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3748522.3779793","type":"proceedings-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:17:49Z","timestamp":1781014669000},"page":"1237-1239","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SAP: Syntactic Attention Pruning for Transformer-based Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2245-0770","authenticated-orcid":false,"given":"Tzu-Yun","family":"Lee","sequence":"first","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7649-7581","authenticated-orcid":false,"given":"Ding-Yong","family":"Hong","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1722-4361","authenticated-orcid":false,"given":"Jan-Jan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jihye Back Namhyuk Ahn and Jangho Kim. 2025. Magnitude attention-based dynamic pruning. Expert Systems with Applications 276 C.","DOI":"10.1016\/j.eswa.2025.126957"},{"key":"e_1_3_2_1_2_1","volume-title":"ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP.","author":"Clark Kevin","unstructured":"Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of BERT's attention. In ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP."},{"key":"e_1_3_2_1_3_1","first-page":"24101","article-title":"A fast post-training pruning framework for transformers","volume":"35","author":"Kwon Woosuk","year":"2022","unstructured":"Woosuk Kwon, Sehoon Kim, Michael W Mahoney, Joseph Hassoun, Kurt Keutzer, and Amir Gholami. 2022. A fast post-training pruning framework for transformers. In NeurIPS. Vol. 35, 24101\u201324116.","journal-title":"NeurIPS."},{"key":"e_1_3_2_1_4_1","volume-title":"Are sixteen heads really better than one? In Advances in Neural Information Processing Systems","author":"Michel Paul","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are sixteen heads really better than one? In Advances in Neural Information Processing Systems. Vol. 32."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Language Resources and Evaluation.","author":"Joakim","unstructured":"Joakim Nivre et al. 2016. Universal Dependencies v1: a multilingual treebank collection. In International Conference on Language Resources and Evaluation."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Bowen Shen Zheng Lin Daren Zha Wei Liu Jian Luan Bin Wang and Weiping Wang. 2024. Pruning large language models to intra-module low-rank architecture with transitional activations. In Findings of ACL 9781\u20139793.","DOI":"10.18653\/v1\/2024.findings-acl.582"},{"key":"e_1_3_2_1_7_1","unstructured":"Mingjie Sun Zhuang Liu Anna Bair and J. Zico Kolter. 2023. A simple and effective pruning approach for large language models. arXiv:2306.11695."},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems.","author":"Vaswani Ashish","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. Vol. 30."},{"key":"e_1_3_2_1_9_1","volume-title":"Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned","author":"Voita Elena","unstructured":"Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich, and Ivan Titov. 2019. Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In Association for Computational Linguistics, 5797\u20135808."},{"key":"e_1_3_2_1_10_1","volume-title":"Bowman","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: a multi-task benchmark and analysis platform for natural language understanding. In ICLR."},{"key":"e_1_3_2_1_11_1","unstructured":"Zhihang Yuan et al. 2024. Llm inference unveiled: survey and roofline model insights. In arXiv: 2402.16363."}],"event":{"name":"SAC '26: 41st ACM\/SIGAPP Symposium on Applied Computing","location":"Grand Hotel Palace Thessaloniki Greece","acronym":"SAC '26","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 41st ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748522.3779793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:35:56Z","timestamp":1781015756000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748522.3779793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":11,"alternative-id":["10.1145\/3748522.3779793","10.1145\/3748522"],"URL":"https:\/\/doi.org\/10.1145\/3748522.3779793","relation":{},"subject":[],"published":{"date-parts":[[2026,3,23]]},"assertion":[{"value":"2026-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}