{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:35:53Z","timestamp":1784248553188,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116312"],"award-info":[{"award-number":["2022ZD0116312"]}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["22&ZD298"],"award-info":[{"award-number":["22&ZD298"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute Guo Qiang at Tsinghua University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3407575","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:23Z","timestamp":1717091783000},"page":"3101-3112","source":"Crossref","is-referenced-by-count":6,"title":["Hyperbolic Pre-Trained Language Model"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5882-8870","authenticated-orcid":false,"given":"Weize","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-7621","authenticated-orcid":false,"given":"Xu","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0151-6178","authenticated-orcid":false,"given":"Yankai","family":"Lin","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaichen","family":"He","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-5165","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref3","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2001"},{"key":"ref4","article-title":"Emergent abilities of large language models","volume-title":"Trans. Mach. Learn. Res.","volume":"2022","author":"Wei","year":"2022"},{"key":"ref5","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref7","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"1907"},{"key":"ref9","article-title":"DeBERTa: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"He","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1515\/9783112316009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21236\/ad0616323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1419"},{"key":"ref13","article-title":"Probing BERT in hyperbolic spaces","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref14","article-title":"Representation tradeoffs for hyperbolic embeddings","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Sala","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1139"},{"key":"ref18","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Clark"},{"key":"ref19","first-page":"140:1140:67","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"J. Mach. Learn. Res.","volume":"21","author":"Raffel","year":"2020"},{"key":"ref20","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"1909"},{"key":"ref21","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","first-page":"6338","article-title":"Poincar embeddings for learning hierarchical representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30, Annu. Conf. Neural Inf. Process. Syst.","author":"Nickel","year":"2017"},{"key":"ref23","first-page":"4465","article-title":"Multi-relational poincar graph embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32: Annu. Conf. Neural Inf. Process. Syst.","author":"Balazevic","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.617"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539333"},{"key":"ref26","first-page":"4869","article-title":"Hyperbolic graph convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32, Annu. Conf. Neural Inf. Process. Syst.","author":"Chami","year":"2019"},{"key":"ref27","first-page":"486","article-title":"Constant curvature graph convolutional networks","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Bachmann","year":"2020"},{"key":"ref28","first-page":"5350","article-title":"Hyperbolic neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 31, Annu. Conf. Neural Inf. Process. Syst.","author":"Ganea","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.104"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.389"},{"key":"ref32","volume-title":"Foundations of Hyperbolic Manifolds","author":"Ratcliffe","year":"2006"},{"key":"ref33","first-page":"3672","article-title":"Lorentzian distance learning for hyperbolic representations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Law","year":"2019"},{"key":"ref34","first-page":"6393","article-title":"Differentiating through the frchet mean","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Lou","year":"2020"},{"key":"ref35","article-title":"Riemannian adaptive optimization methods","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Bcigneul","year":"2019"},{"key":"ref36","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"You"},{"key":"ref37","article-title":"Geoopt: Riemannian optimization in pyTorch","author":"Kochurov","year":"2020"},{"key":"ref38","article-title":"A large batch optimizer reality check: Traditional, generic optimizers suffice across batch sizes","author":"Nado","year":"2021"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1439"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00240"},{"key":"ref42","first-page":"777","article-title":"Resolving complex cases of definite pronouns: The winograd schema challenge","volume-title":"Proc. Joint Conf. Empirical Methods Natural Lang. Process. Comput. Natural Lang. Learn.","author":"Rahman","year":"2012"},{"key":"ref43","first-page":"552","article-title":"The winograd schema challenge","volume-title":"Proc. 13th Int. Conf. Princ. Knowl. Representation Reasoning","author":"Levesque","year":"2012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2002"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i4.2734"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8122"},{"key":"ref47","first-page":"87","article-title":"Ultra-fine entity typing","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Choi","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"ref49","first-page":"142","article-title":"Introduction to the conll-2003 shared task: Language-independent named entity recognition","volume-title":"Proc. 7th Conf. Natural Lang. Learn.","author":"Sang","year":"2003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.248"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.142"},{"key":"ref53","first-page":"13843","article-title":"Re-tacred: Addressing shortcomings of the TACRED dataset","volume-title":"Proc. 35th AAAI Conf. Artif. Intell., AAAI 33rd Conf. Innov. Appl. Artif. Intell, 11th Symp. Educ. Adv. Artif. Intell.","author":"Stoica","year":"2021"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W18-5446","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-5801"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref59","article-title":"SearchQA: A new q&a dataset augmented with context from a search engine","author":"Dunn","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1259"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.582"},{"key":"ref63","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref65","article-title":"MCTensor: A high-precision deep learning library with multi-component floating-point","author":"Yu","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7131-2_100141"},{"key":"ref67","first-page":"161","article-title":"An improved baseline for sentence-level relation extraction","volume-title":"Proc. 2nd Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 12th Int. Joint Conf. Natural Lang. Process.","author":"Zhou","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10542420.pdf?arnumber=10542420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:09:42Z","timestamp":1725685782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407575","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}