{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:43:25Z","timestamp":1771699405323,"version":"3.50.1"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030604493","type":"print"},{"value":"9783030604509","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60450-9_29","type":"book-chapter","created":{"date-parts":[[2020,10,5]],"date-time":"2020-10-05T15:18:51Z","timestamp":1601911131000},"page":"359-371","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models"],"prefix":"10.1007","author":[{"given":"Zihan","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Yuncong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Lu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Rao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,2]]},"reference":[{"key":"29_CR1","unstructured":"Bhandare, A., et al.: Efficient 8-bit quantization of transformer neural machine language translation model. arXiv preprint arXiv:1906.00532 (2019)"},{"key":"29_CR2","unstructured":"Cheong, R., Daniel, R.: Transformers.zip: compressing transformers with pruning and quantization. Technical report, Stanford University, Stanford, California (2019). https:\/\/web.stanford.edu\/class\/cs224n\/reports\/custom\/15763707.pdf"},{"key":"29_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ: hessian aware quantization of neural networks with mixed-precision. In: ICCV, pp. 293\u2013302 (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"29_CR5","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and Huffman coding. In: ICLR (2016)"},{"key":"29_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"29_CR7","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite BERT for self-supervised learning of language representations. In: ICLR (2019)"},{"key":"29_CR8","unstructured":"Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: NIPS, pp. 345\u2013353 (2017)"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Ma, R., Liu, Q., Yu, K.: Highly efficient neural network language model compression using soft binarization training. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 62\u201369. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003744"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Prato, G., Charlaix, E., Rezagholizadeh, M.: Fully quantized transformer for machine translation. arXiv preprint arXiv:1910.10485 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Q-BERT: hessian based ultra low precision quantization of BERT. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Shi, K., Yu, K.: Structured word embedding for low memory neural network language model. In: INTERSPEECH, pp. 1254\u20131258 (2018)","DOI":"10.21437\/Interspeech.2018-1057"},{"key":"29_CR13","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: Glue: a multi-task benchmark and analysis platform for natural language understanding. In: ICLR (2019)","DOI":"10.18653\/v1\/W18-5446"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: CVPR, pp. 8612\u20138620 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Zafrir, O., Boudoukh, G., Izsak, P., Wasserblat, M.: Q8BERT: quantized 8bit BERT. In: NIPS EMC$$^2$$ Workshop (2019)","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"29_CR17","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)"},{"key":"29_CR18","unstructured":"Zhu, C., Han, S., Mao, H., Dally, W.J.: Trained ternary quantization. In: ICLR (2017)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60450-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T05:29:29Z","timestamp":1669094969000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60450-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030604493","9783030604509"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60450-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"2 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"320","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"100","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}