{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T18:46:58Z","timestamp":1781808418767,"version":"3.54.5"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007785","name":"Jinan Science and Technology Bureau","doi-asserted-by":"publisher","award":["202333043"],"award-info":[{"award-number":["202333043"]}],"id":[{"id":"10.13039\/100007785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,5]]},"DOI":"10.1109\/cscwd64889.2025.11033399","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:24:40Z","timestamp":1750699480000},"page":"910-915","source":"Crossref","is-referenced-by-count":1,"title":["Research on Key Methods for Extracting High-Quality Chinese Corpus Based on Common Crawl"],"prefix":"10.1109","author":[{"given":"Lianhui","family":"Xiao","sequence":"first","affiliation":[{"name":"Qilu University of Technology,Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, (National Supercomputer Center in Jinan), (Shandong Academy of Sciences),Jinan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Qilu University of Technology,Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, (National Supercomputer Center in Jinan), (Shandong Academy of Sciences),Jinan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Qilu University of Technology,Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, (National Supercomputer Center in Jinan), (Shandong Academy of Sciences),Jinan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qilu University of Technology,Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, (National Supercomputer Center in Jinan), (Shandong Academy of Sciences),Jinan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fulai","family":"Liu","sequence":"additional","affiliation":[{"name":"Qilu University of Technology,Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, (National Supercomputer Center in Jinan), (Shandong Academy of Sciences),Jinan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Yuan 1.0: Large-scale pre-trained language model in zero-shot and few-shot learning","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Pangu-o: Large-scale autoregressive pretrained chinese language models with auto-parallel computation","author":"Zeng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2021.102761"},{"key":"ref4","volume":"2302","author":"Touvron","year":"2023","journal-title":"Open and efficient foundation language models"},{"key":"ref5","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"issue":"3","key":"ref7","first-page":"30","article-title":"Nkcorpus: Extracting high quality large chinese dataset from web data","volume":"4","author":"Dongwen","year":"2022","journal-title":"Frontiers of Data and Domputing"},{"key":"ref8","first-page":"79 155","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only","volume":"36","author":"Penedo","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Cluecorpus2020: A large-scale chinese corpus for pre-training language model","author":"Xu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020","journal-title":"arXiv preprint"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"140","key":"ref12","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.07.001"},{"key":"ref14","volume-title":"Common crawl website","author":"Skrenta","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63031-7_22"},{"key":"ref17","first-page":"6","article-title":"Tocp: A dataset for chinese profanity processing","volume-title":"Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.osnem.2021.100182"},{"key":"ref19","article-title":"Eva: An open-domain chinese dialogue system with large-scale generative pre-training","author":"Zhou","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield"}],"event":{"name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","location":"Compiegne, France","start":{"date-parts":[[2025,5,5]]},"end":{"date-parts":[[2025,5,7]]}},"container-title":["2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11033175\/11033221\/11033399.pdf?arnumber=11033399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:13:23Z","timestamp":1750745603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cscwd64889.2025.11033399","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]}}}