{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:22:53Z","timestamp":1775010173051,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,22]]},"DOI":"10.1109\/icccs55155.2022.9846198","type":"proceedings-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:02:40Z","timestamp":1660593760000},"page":"27-31","source":"Crossref","is-referenced-by-count":4,"title":["Post-Training Quantization for Longformer with Chunkwise Quantization Granularity and Optimized Percentile"],"prefix":"10.1109","author":[{"given":"Qibin","family":"Chen","sequence":"first","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Yijin","family":"Teng","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Kai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Qiang","family":"Duan","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Xinxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology"}]}],"member":"263","reference":[{"key":"ref10","first-page":"291","article-title":"A Survey of Quantization Methods for Efficient Neural Network Inference","author":"gholami","year":"2021","journal-title":"Low-Power Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref12","first-page":"3007","article-title":"Analytical guarantees on numerical precision of deep neural networks","volume":"70","author":"sakr","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref13","first-page":"4486","article-title":"Same, same but different: Recovering neural network quantization error through weight factorization","author":"meller","year":"2019","journal-title":"Int Conference on Machine Learning"},{"key":"ref14","article-title":"Post-training 4-bit quantization of convolution networks for rapid-deployment","author":"banner","year":"2018"},{"key":"ref15","article-title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","author":"bhandare","year":"2019"},{"key":"ref16","article-title":"Training with quantization noise for extreme fixed-point compression","author":"fan","year":"2020","journal-title":"International Conference on Learning Representations(ICLR)"},{"key":"ref17","article-title":"Fully quantized transformer for improved translation","author":"prato","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref4","article-title":"Linformer: Selfattention with linear complexity","author":"wang","year":"2020"},{"key":"ref3","article-title":"Masked language modeling for proteins via linearly scalable long-context transformers","author":"choromanski","year":"2020"},{"key":"ref6","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"zaheer","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref5","article-title":"Reformer: The effcient transformer","author":"kitaev","year":"2019","journal-title":"International Conference on Learning Representations(ICLR)"},{"key":"ref8","first-page":"5506","article-title":"I-BERT: Integer-only BERT Quantization","author":"kim","year":"2021","journal-title":"Int Conference on Machine Learning"},{"key":"ref7","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"International Conference on Learning Representations(ICLR)"},{"key":"ref1","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref9","article-title":"Nvidia 8-bit inference with tensorrt","author":"migacz","year":"2017","journal-title":"GPU Technology Conference"}],"event":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","location":"Wuhan, China","start":{"date-parts":[[2022,4,22]]},"end":{"date-parts":[[2022,4,25]]}},"container-title":["2022 7th International Conference on Computer and Communication Systems (ICCCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9845797\/9845820\/09846198.pdf?arnumber=9846198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:20Z","timestamp":1662409460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9846198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,22]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icccs55155.2022.9846198","relation":{},"subject":[],"published":{"date-parts":[[2022,4,22]]}}}