{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:03:55Z","timestamp":1781665435218,"version":"3.54.5"},"reference-count":65,"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 Plan","award":["2020AAA0106600"],"award-info":[{"award-number":["2020AAA0106600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2020"],"award-info":[{"award-number":["U19B2020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172039"],"award-info":[{"award-number":["62172039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2023.3267618","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T18:12:02Z","timestamp":1681755122000},"page":"1061-1074","source":"Crossref","is-referenced-by-count":16,"title":["Can Pretrained English Language Models Benefit Non-English NLP Systems in Low-Resource Scenarios?"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1615-1885","authenticated-orcid":false,"given":"Zewen","family":"Chi","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-7520","authenticated-orcid":false,"given":"Heyan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2311","authenticated-orcid":false,"given":"Xian-Ling","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"140","key":"ref2","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":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"ref5","first-page":"5926","article-title":"MASS: Masked sequence to sequence pre-training for language generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2019"},{"key":"ref6","first-page":"4411","article-title":"XTREME: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Hu","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref10","article-title":"Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.653"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"ref14","first-page":"7057","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Conneau","year":"2019"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref16","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref17","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref20","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1077"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref28","article-title":"Cross-lingual ability of multilingual BERT: An empirical study","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karthikeyan","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1252"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.308"},{"key":"ref32","article-title":"On learning universal representations across languages","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6480"},{"key":"ref35","article-title":"Multilingual alignment of contextual word representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cao","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.starsem-1.22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.284"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.265"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.210"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.348"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6256"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.248"},{"key":"ref45","article-title":"DeltaLM: Encoder-decoder pre-training for language generation and translation by augmenting pretrained multilingual encoders","author":"Ma","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref48","article-title":"Cross-lingual transferring of pre-trained contextualized language models","author":"Li","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref51","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref52","first-page":"12","article-title":"Can monolingual pretrained models help cross-lingual classification","volume-title":"Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 10th Int. Joint Conf. Natural Lang. Process.","author":"Chi","year":"2020"},{"key":"ref53","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref55","article-title":"Word translation without parallel data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lample","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.147"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1382"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00317"},{"key":"ref59","article-title":"Universal dependencies 2.5","author":"Zeman","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1178"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref63","first-page":"1118","article-title":"Cross-language text classification using structural correspondence learning","volume-title":"Proc. 48th Annu. Meeting Assoc. Comput. Linguistics","author":"Prettenhofer","year":"2010"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.358"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10103146.pdf?arnumber=10103146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:17:59Z","timestamp":1705688279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10103146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3267618","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}