{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:40:02Z","timestamp":1755877202723,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,22]]},"DOI":"10.1145\/3654823.3654845","type":"proceedings-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T16:20:33Z","timestamp":1716999633000},"page":"116-122","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SLP-LMNMT: Source Language Prediction in Bilingual and Many-to-One Neural Machine Translation Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9653-0337","authenticated-orcid":false,"given":"Dongxing","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Geographical Science, Beijing Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2352-2675","authenticated-orcid":false,"given":"Dongdong","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Information Science and Technology University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 642\u2013652","author":"Bao Hangbo","year":"2020","unstructured":"Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Jianfeng Gao, Songhao Piao, Ming Zhou, 2020. Unilmv2: Pseudo-masked language models for unified language model pre-training. In International conference on machine learning. PMLR, 642\u2013652."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1536"},{"key":"e_1_3_2_1_3_1","volume-title":"Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems 32","author":"Dong Li","year":"2019","unstructured":"Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019. Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.740"},{"key":"e_1_3_2_1_5_1","volume-title":"A synopsis of linguistic theory","author":"Firth John","year":"1930","unstructured":"John Firth. 1957. A synopsis of linguistic theory, 1930-1955. Studies in linguistic analysis (1957), 10\u201332."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR, 4475\u20134483","author":"Huang Xiao\u00a0Shi","year":"2020","unstructured":"Xiao\u00a0Shi Huang, Felipe Perez, Jimmy Ba, and Maksims Volkovs. 2020. Improving transformer optimization through better initialization. In International Conference on Machine Learning. PMLR, 4475\u20134483."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of NAACL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_9_1","volume-title":"FBK\u2019s Multilingual Neural Machine Translation System for IWSLT 2017. In Proceedings of the 14th International Workshop on Spoken Language Translation (IWSLT","author":"Lakew M","year":"2017","unstructured":"Surafel\u00a0M Lakew, Quintino\u00a0F Lotito, Marco Turchi, Matteo Negri, and Marcello Federico. 2017. FBK\u2019s Multilingual Neural Machine Translation System for IWSLT 2017. In Proceedings of the 14th International Workshop on Spoken Language Translation (IWSLT 2017). 35\u201341."},{"key":"e_1_3_2_1_10_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_12_1","volume-title":"Regression Loss in Transformer-based Supervised Neural Machine Translation. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL 16, 4","author":"Li Dongxing","year":"2021","unstructured":"Dongxing Li and Zuying Luo. 2021. Regression Loss in Transformer-based Supervised Neural Machine Translation. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL 16, 4 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6344"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 27th international conference on computational linguistics. 1952\u20131962","author":"Liu Xin","year":"2018","unstructured":"Xin Liu, Qingcai Chen, Chong Deng, Huajun Zeng, Jing Chen, Dongfang Li, and Buzhou Tang. 2018. Lcqmc: A large-scale chinese question matching corpus. In Proceedings of the 27th international conference on computational linguistics. 1952\u20131962."},{"key":"e_1_3_2_1_15_1","volume-title":"The natural language decathlon: Multitask learning as question answering. arXiv preprint arXiv:1806.08730","author":"McCann Bryan","year":"2018","unstructured":"Bryan McCann, Nitish\u00a0Shirish Keskar, Caiming Xiong, and Richard Socher. 2018. The natural language decathlon: Multitask learning as question answering. arXiv preprint arXiv:1806.08730 (2018)."},{"key":"e_1_3_2_1_16_1","volume-title":"Mixed precision training. arXiv preprint arXiv:1710.03740","author":"Micikevicius Paulius","year":"2017","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, 2017. Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)."},{"key":"e_1_3_2_1_17_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_18_1","volume-title":"Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems 26","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg\u00a0S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_19_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 5926\u20135936","author":"Song Kaitao","year":"2019","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2019. MASS: Masked Sequence to Sequence Pre-training for Language Generation. In International Conference on Machine Learning. PMLR, 5926\u20135936."},{"key":"e_1_3_2_1_22_1","volume-title":"BartPho: pre-trained sequence-to-sequence models for Vietnamese. arXiv preprint arXiv:2109.09701","author":"Tran Nguyen\u00a0Luong","year":"2021","unstructured":"Nguyen\u00a0Luong Tran, Duong\u00a0Minh Le, and Dat\u00a0Quoc Nguyen. 2021. BartPho: pre-trained sequence-to-sequence models for Vietnamese. arXiv preprint arXiv:2109.09701 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000\u20136010","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000\u20136010."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 3266\u20133280","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel\u00a0R Bowman. 2019. SuperGLUE: a stickier benchmark for general-purpose language understanding systems. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 3266\u20133280."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"e_1_3_2_1_27_1","volume-title":"Nezha: Neural contextualized representation for chinese language understanding. arXiv preprint arXiv:1909.00204","author":"Wei Junqiu","year":"2019","unstructured":"Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen, and Qun Liu. 2019. Nezha: Neural contextualized representation for chinese language understanding. arXiv preprint arXiv:1909.00204 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"TENER: adapting transformer encoder for named entity recognition. arXiv preprint arXiv:1911.04474","author":"Yan Hang","year":"2019","unstructured":"Hang Yan, Bocao Deng, Xiaonan Li, and Xipeng Qiu. 2019. TENER: adapting transformer encoder for named entity recognition. arXiv preprint arXiv:1911.04474 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962","author":"You Yang","year":"2019","unstructured":"Yang You, Jing Li, Sashank Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, and Cho-Jui Hsieh. 2019. Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1083"}],"event":{"name":"CACML 2024: 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning","acronym":"CACML 2024","location":"Shanghai China"},"container-title":["Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654823.3654845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654823.3654845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:16:15Z","timestamp":1755875775000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654823.3654845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":30,"alternative-id":["10.1145\/3654823.3654845","10.1145\/3654823"],"URL":"https:\/\/doi.org\/10.1145\/3654823.3654845","relation":{},"subject":[],"published":{"date-parts":[[2024,3,22]]},"assertion":[{"value":"2024-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}