{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:57:07Z","timestamp":1777892227219,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2146171, CPS-2313109"],"award-info":[{"award-number":["CNS-2146171, CPS-2313109"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ONR","award":["N00014-23-C-1016"],"award-info":[{"award-number":["N00014-23-C-1016"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3651931","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"1548-1557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-070X","authenticated-orcid":false,"given":"Yun-Wei","family":"Chu","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2970-7336","authenticated-orcid":false,"given":"Dong-Jun","family":"Han","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2771-3521","authenticated-orcid":false,"given":"Christopher G.","family":"Brinton","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Lane","author":"Beutel Daniel J.","year":"2020","unstructured":"Daniel J. Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Titouan Parcollet, and Nicholas D. Lane. 2020. Flower: A Friendly Federated Learning Research Framework. ArXiv , Vol. abs\/2007.14390 (2020)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_2_3_1","article-title":"Beyond English-Centric Multilingual Machine Translation","volume":"22","author":"Fan Angela","year":"2021","unstructured":"Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur \u00c7elebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, and Armand Joulin. 2021. Beyond English-Centric Multilingual Machine Translation. J. Mach. Learn. Res. , Vol. 22 (2021), 107:1--107:48.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00413"},{"key":"e_1_3_2_2_5_1","volume-title":"FedNER: Medical Named Entity Recognition with Federated Learning. arXiv: Computation and Language","author":"Ge Suyu","year":"2020","unstructured":"Suyu Ge, Fangzhao Wu, Chuhan Wu, Tao Qi, Yongfeng Huang, and Xing Xie. 2020. FedNER: Medical Named Entity Recognition with Federated Learning. arXiv: Computation and Language (2020)."},{"key":"e_1_3_2_2_6_1","article-title":"Compression of Deep Learning Models for Text: A Survey","volume":"16","author":"Gupta Manish","year":"2020","unstructured":"Manish Gupta and Puneet Agrawal. 2020. Compression of Deep Learning Models for Text: A Survey. ACM Trans. Knowl. Discov. Data , Vol. 16 (2020), 61:1--61:55.","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.441"},{"key":"e_1_3_2_2_8_1","unstructured":"Chi-Yang Hsu Yun-Wei Chu Ting-Hao 'Kenneth' Huang and Lun-Wei Ku. 2021. Plot and Rework: Modeling Storylines for Visual Storytelling. In Findings. https:\/\/api.semanticscholar.org\/CorpusID:234682123"},{"key":"e_1_3_2_2_9_1","volume-title":"Ananda Theertha Suresh, and Dave Bacon","author":"Konecn\u00fd Jakub","year":"2016","unstructured":"Jakub Konecn\u00fd, H. B. McMahan, Felix X. Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. 2016. Federated Learning: Strategies for Improving Communication Efficiency. ArXiv , Vol. abs\/1610.05492 (2016)."},{"key":"e_1_3_2_2_10_1","volume-title":"Revealing the Dark Secrets of BERT. In Conference on Empirical Methods in Natural Language Processing.","author":"Kovaleva Olga","year":"2019","unstructured":"Olga Kovaleva, Alexey Romanov, Anna Rogers, and Anna Rumshisky. 2019. Revealing the Dark Secrets of BERT. In Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_2_11_1","volume-title":"Deduplicating Training Data Makes Language Models Better. In Annual Meeting of the Association for Computational Linguistics.","author":"Lee Katherine","year":"2021","unstructured":"Katherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang, Douglas Eck, Chris Callison-Burch, and Nicholas Carlini. 2021. Deduplicating Training Data Makes Language Models Better. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.13"},{"key":"e_1_3_2_2_14_1","volume-title":"Federated Learning Meets Natural Language Processing: A Survey. ArXiv","author":"Liu Ming","year":"2021","unstructured":"Ming Liu, Stella Ho, Mengqi Wang, Longxiang Gao, Yuan Jin, and Heng Zhang. 2021. Federated Learning Meets Natural Language Processing: A Survey. ArXiv , Vol. abs\/2107.12603 (2021)."},{"key":"e_1_3_2_2_15_1","unstructured":"H. B. McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Ag\u00fcera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In AISTATS."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.fl4nlp-1.4"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1050"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Kishore Papineni Salim Roukos Todd Ward and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In ACL.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.186"},{"key":"e_1_3_2_2_20_1","volume-title":"A Call for Clarity in Reporting BLEU Scores. ArXiv","author":"Post Matt","year":"2018","unstructured":"Matt Post. 2018. A Call for Clarity in Reporting BLEU Scores. ArXiv , Vol. abs\/1804.08771 (2018)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.321"},{"key":"e_1_3_2_2_22_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners."},{"key":"e_1_3_2_2_23_1","volume-title":"Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation. ArXiv","author":"Raganato Alessandro","year":"2020","unstructured":"Alessandro Raganato, Yves Scherrer, and J\u00f6rg Tiedemann. 2020. Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation. ArXiv , Vol. abs\/2002.10260 (2020)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.fl4nlp-1.2"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"e_1_3_2_2_27_1","unstructured":"Jun Shu Qi Xie Lixuan Yi Qian Zhao Sanping Zhou Zongben Xu and Deyu Meng. 2019. Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting. In Neural Information Processing Systems."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.220"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.52"},{"key":"e_1_3_2_2_30_1","volume-title":"Synthesizer: Rethinking Self-Attention in Transformer Models. In International Conference on Machine Learning.","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Dara Bahri, Donald Metzler, Da-Cheng Juan, Zhe Zhao, and Che Zheng. 2020. Synthesizer: Rethinking Self-Attention in Transformer Models. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_31_1","volume-title":"Andr\u00e9 F. T. Martins, Peter Milder, Colin Raffel, Edwin Simpson, Noam Slonim, Niranjan Balasubramanian, Leon Derczynski, and Roy Schwartz.","author":"Treviso Marcos Vin\u00edcius","year":"2022","unstructured":"Marcos Vin\u00edcius Treviso, Tianchu Ji, Ji-Ung Lee, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Pedro Henrique Martins, Andr\u00e9 F. T. Martins, Peter Milder, Colin Raffel, Edwin Simpson, Noam Slonim, Niranjan Balasubramanian, Leon Derczynski, and Roy Schwartz. 2022. Efficient Methods for Natural Language Processing: A Survey. ArXiv , Vol. abs\/2209.00099 (2022)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.101"},{"key":"e_1_3_2_2_33_1","volume-title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv , Vol. abs\/1910.03771 (2019)."},{"key":"e_1_3_2_2_34_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. ArXiv , Vol. abs\/2205.01068 (2022)."},{"key":"e_1_3_2_2_35_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)","author":"Junczys-Dowmunt Marcin","year":"2016","unstructured":"Micha? Ziemski, Marcin Junczys-Dowmunt, and Bruno Pouliquen. 2016. The United Nations Parallel Corpus v1.0. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16). European Language Resources Association (ELRA), Portorovz, Slovenia, 3530--3534. https:\/\/aclanthology.org\/L16--1561"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651931","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3651931","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3651931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:27:56Z","timestamp":1755822476000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651931"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":36,"alternative-id":["10.1145\/3589335.3651931","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3651931","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}