{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:10:02Z","timestamp":1755846602601,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62076009\/61732001"],"award-info":[{"award-number":["62076009\/61732001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,23]]},"DOI":"10.1145\/3579654.3579728","type":"proceedings-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T16:09:40Z","timestamp":1678810180000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Entangled Representation Learning: A Bidirectional Encoder Decoder Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8402-6253","authenticated-orcid":false,"given":"Jiqun","family":"Chu","sequence":"first","affiliation":[{"name":"Peking University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-9683","authenticated-orcid":false,"given":"Zuoquan","family":"Lin","sequence":"additional","affiliation":[{"name":"Peking University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413402"},{"key":"e_1_3_2_1_3_1","unstructured":"St\u00e9phane Clinchant Kweon\u00a0Woo Jung and Vassilina Nikoulina. 2019. On the use of BERT for Neural Machine Translation. CoRR abs\/1909.12744(2019). arXiv:1909.12744http:\/\/arxiv.org\/abs\/1909.12744"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Alexis Conneau Douwe Kiela Holger Schwenk Lo\u00efc Barrault and Antoine Bordes. 2017. Supervised Learning of Universal Sentence Representations from Natural Language Inference Data. CoRR abs\/1705.02364(2017). arXiv:1705.02364http:\/\/arxiv.org\/abs\/1705.02364","DOI":"10.18653\/v1\/D17-1070"},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929(2020). arXiv:2010.11929https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1045"},{"key":"e_1_3_2_1_7_1","unstructured":"Zhihao Fan Yeyun Gong Dayiheng Liu Zhongyu Wei Siyuan Wang Jian Jiao Nan Duan Ruofei Zhang and Xuanjing Huang. 2021. Mask Attention Neorks: Rethinking and Strengthen Transformer. CoRR abs\/2103.13597(2021). arXiv:2103.13597https:\/\/arxiv.org\/abs\/2103.13597"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Miguel Gra\u00e7a Yunsu Kim Julian Schamper Shahram Khadivi and Hermann Ney. 2019. Generalizing Back-Translation in Neural Machine Translation. CoRR abs\/1906.07286(2019). arXiv:1906.07286http:\/\/arxiv.org\/abs\/1906.07286","DOI":"10.18653\/v1\/W19-5205"},{"key":"e_1_3_2_1_9_1","volume-title":"Dual Learning for Machine Translation. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","author":"He Di","year":"2016","unstructured":"Di He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma. 2016. Dual Learning for Machine Translation. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, Daniel\u00a0D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.). 820\u2013828. https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/5b69b9cb83065d403869739ae7f0995e-Abstract.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-2703"},{"key":"e_1_3_2_1_11_1","unstructured":"Andrej Karpathy and Li Fei-Fei. 2014. Deep Visual-Semantic Alignments for Generating Image Descriptions. CoRR abs\/1412.2306(2014). arXiv:1412.2306http:\/\/arxiv.org\/abs\/1412.2306"},{"key":"e_1_3_2_1_12_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2015","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_13_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461(2019). arXiv:1910.13461http:\/\/arxiv.org\/abs\/1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2019. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461(2019). arXiv:1910.13461http:\/\/arxiv.org\/abs\/1910.13461"},{"key":"e_1_3_2_1_14_1","unstructured":"Tsung-Yi Lin Michael Maire Serge\u00a0J. Belongie Lubomir\u00a0D. Bourdev Ross\u00a0B. Girshick James Hays Pietro Perona Deva Ramanan Piotr Doll\u00e1r and C.\u00a0Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. CoRR abs\/1405.0312(2014). arXiv:1405.0312http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_2_1_15_1","unstructured":"Ron Mokady Amir Hertz and Amit\u00a0H. Bermano. 2021. ClipCap: CLIP Prefix for Image Captioning. CoRR abs\/2111.09734(2021). arXiv:2111.09734https:\/\/arxiv.org\/abs\/2111.09734"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Myle Ott Sergey Edunov Alexei Baevski Angela Fan Sam Gross Nathan Ng David Grangier and Michael Auli. 2019. fairseq: A Fast Extensible Toolkit for Sequence Modeling. CoRR abs\/1904.01038(2019). arXiv:1904.01038http:\/\/arxiv.org\/abs\/1904.01038","DOI":"10.18653\/v1\/N19-4009"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Myle Ott Sergey Edunov David Grangier and Michael Auli. 2018. Scaling Neural Machine Translation. CoRR abs\/1806.00187(2018). arXiv:1806.00187http:\/\/arxiv.org\/abs\/1806.00187","DOI":"10.18653\/v1\/W18-6301"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_20_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_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-2323"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1009"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"e_1_3_2_1_24_1","volume-title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation. CoRR abs\/1905.02450(2019). arXiv:1905.02450http:\/\/arxiv.org\/abs\/1905.02450","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. CoRR abs\/1905.02450(2019). arXiv:1905.02450http:\/\/arxiv.org\/abs\/1905.02450"},{"key":"e_1_3_2_1_25_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc\u00a0V. Le. 2014. Sequence to Sequence Learning with Neural Networks. CoRR abs\/1409.3215(2014). arXiv:1409.3215http:\/\/arxiv.org\/abs\/1409.3215"},{"key":"e_1_3_2_1_26_1","unstructured":"Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jonathon Shlens and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. CoRR abs\/1512.00567(2015). arXiv:1512.00567http:\/\/arxiv.org\/abs\/1512.00567"},{"key":"e_1_3_2_1_27_1","unstructured":"Sho Takase and Shun Kiyono. 2021. Lessons on Parameter Sharing across Layers in Transformers. CoRR abs\/2104.06022(2021). arXiv:2104.06022https:\/\/arxiv.org\/abs\/2104.06022"},{"key":"e_1_3_2_1_28_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van\u00a0der Maaten Laurens","year":"2008","unstructured":"Laurens van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna\u00a0M. Wallach, Rob Fergus, S.\u00a0V.\u00a0N. Vishwanathan, and Roman Garnett (Eds.). 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Jesse Vig and Yonatan Belinkov. 2019. Analyzing the Structure of Attention in a Transformer Language Model. CoRR abs\/1906.04284(2019). arXiv:1906.04284http:\/\/arxiv.org\/abs\/1906.04284","DOI":"10.18653\/v1\/W19-4808"},{"key":"e_1_3_2_1_31_1","unstructured":"Tsung-Hsien Wen Milica Gasic Nikola Mrksic Lina\u00a0Maria Rojas-Barahona Pei-Hao Su Stefan Ultes David Vandyke and Steve\u00a0J. Young. 2016. A Network-based End-to-End Trainable Task-oriented Dialogue System. CoRR abs\/1604.04562(2016). arXiv:1604.04562http:\/\/arxiv.org\/abs\/1604.04562"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015466"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Xia Yingce","year":"2017","unstructured":"Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, and Tie-Yan Liu. 2017. Dual Supervised Learning. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017(Proceedings of Machine Learning Research, Vol.\u00a070), Doina Precupand Yee\u00a0Whye Teh (Eds.). PMLR, 3789\u20133798. http:\/\/proceedings.mlr.press\/v70\/xia17a.html"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Xia Yingce","year":"2018","unstructured":"Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, and Tie-Yan Liu. 2018. Model-Level Dual Learning. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018(Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer\u00a0G. Dy and Andreas Krause (Eds.). PMLR, 5379\u20135388. http:\/\/proceedings.mlr.press\/v80\/xia18a.html"},{"key":"e_1_3_2_1_35_1","unstructured":"Yizhe Zhang Siqi Sun Michel Galley Yen-Chun Chen Chris Brockett Xiang Gao Jianfeng Gao Jingjing Liu and Bill Dolan. 2019. DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation. CoRR abs\/1911.00536(2019). arXiv:1911.00536http:\/\/arxiv.org\/abs\/1911.00536"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11248"},{"key":"e_1_3_2_1_37_1","unstructured":"Jinhua Zhu Yingce Xia Lijun Wu Di He Tao Qin Wengang Zhou Houqiang Li and Tie-Yan Liu. 2020. Incorporating BERT into Neural Machine Translation. CoRR abs\/2002.06823(2020). arXiv:2002.06823https:\/\/arxiv.org\/abs\/2002.06823"}],"event":{"name":"ACAI 2022: 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","acronym":"ACAI 2022","location":"Sanya China"},"container-title":["Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579728","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579654.3579728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:57:04Z","timestamp":1755845824000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":37,"alternative-id":["10.1145\/3579654.3579728","10.1145\/3579654"],"URL":"https:\/\/doi.org\/10.1145\/3579654.3579728","relation":{},"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"2023-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}