自然语言处理

机器翻译

081104-模式识别与智能系统

自然语言处理

   

• PhD in Pattern Recognition, 2015-2019

  Institute of Automation Chinese Academy of Sciences

• MEng in Automatics, 2012-2015

  Beijing Jiaotong University

• BSc in Automatics, 2008-2012

  Beijing Jiaotong University

赵阳，中国科学院自动化研究所副研究员、硕士生导师，主要从事自然语言处理、机器翻译和知识图谱等相关研究和系统开发工作。在国际权威学术期刊（ACM/IEEE TASLP、ACM TALLIP、AI等）和一流学术会议（AAAI、IJCAI、ACL、EMNLP、COLING等）上发表论文三十余篇，获得第十九届全国机器翻译大会CCMT 2023最佳论文，出版译著一部《神经机器翻译》。目前担任国际学术期刊 ACM TALLIP 副主编（Associate Editor），并多次在ACL、COLING、EMNLP、IJCAI等国际权威学术会议担任程序委员会委员等职务，担任中文信息学会开源情报分析专委会委员，中文信息学会青年工作委员会委员，中文信息学会机器翻译专委会委员，担任CCMT 2023 前沿趋势论坛主席和COLING 2020 出版主席。作为负责人和技术骨干承担多个国家自然基金项目、国家重点研发计划子课题和特定领域应用项目等

   

[1] 赵阳, 张旭, 张翔宇, 刘春阳, 周玉. 神经机器翻译模型的训练方法、翻译方法及装置. CN: CN115345181A, 2022-11-15.
[2] 张家俊, 李鑫, 赵阳, 宗成庆. 对比学习模型的训练方法及装置、汉字表示方法及装置. CN: CN115062787A, 2022-09-16.
[3] 张家俊, 李鑫, 赵阳, 宗成庆. 中文拼写检错纠错方法、装置、电子设备及存储介质. CN: CN115081430A, 2022-09-20.
[4] 赵阳, 张家俊, 周玉, 宗成庆. 基于知识图谱的神经机器翻译方法、装置、设备及介质. CN: CN114118104A, 2022-03-01.
[5] 赵阳, 马聪, 张亚萍, 周玉. 基于多任务训练的端到端图像文本翻译方法、系统、装置. CN: CN113011202A, 2021-06-22.
[6] 赵阳, 马聪, 张亚萍, 周玉. 基于多任务训练的端到端图像文本翻译方法、系统、装置. CN: CN113011202B, 2023-07-25.
[7] 张家俊, 周玉, 赵阳, 宗成庆, 杨里. 神经机器翻译方法以及神经机器翻译装置. US: CN111401080A, 2020-07-10.
[8] 张家俊, 赵阳, 宗成庆. 提高神经机器翻译准确度的方法、翻译方法及系统和设备. CN: CN107943795A, 2018-04-20.
[9] 张家俊, 赵阳, 王亦宁, 宗成庆. 基于神经机器翻译系统的单词预测方法及系统. CN: CN106844352A, 2017-06-13.

–2024

Cong Ma, Yaping Zhang, Yang Zhao, Yu Zhou, and Chengqing Zong. 2023. Vector Quantization Knowledge Transfer For End-to-end text image machine translation. Accepted by 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024).

Yupu Liang, Yaping Zhang, Cong Ma, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou. Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling. Accepted by The 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024). Mexico City, Mexico. June 16-21, 2024.

Cong Ma, Yaping Zhang, Zhiyang Zhang, Yupu Liang, Yang Zhao, Yu Zhou, Chengqing Zong. Born a BabNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation. Accepted by The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Torino, Italia. May 20-25, 2024.

–2023

Journal

Yang Zhao, Jiajun Zhang, Chengqing Zong. 2023. Transformer: A General Framework from Machine Translation to Others. Machine Intelligence Research 20, 514–538 (2023). https://doi.org/10.1007/s11633-022-1393-5.

Lu Xiang, Yang Zhao, Junnan Zhu, Yu Zhou, Chengqing Zong. 2023. Zero-shot language extension for dialogue state tracking via pre-trained models and multi-auxiliary-tasks fine-tuning. Knowledge-Based Systems, Volume 259, 2023, 110015.

Cong Ma, Xu Han, Linghui Wu, Yaping Zhang, Yang Zhao, Yu Zhou, and Chengqing Zong. 2023. Modal Contrastive Learning based End-to-End Text Image Machine Translation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, doi: 10.1109/TASLP.2023.3324540.

Conference

Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, and Chengqing Zong. 2023. CCIM: Cross-modal Cross-lingual Interactive Image Translation. In Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023), pages 4959–4965.

Zixuan Ren, Yang Zhao, and Chengqing Zong. 2023. Towards Informative Open-ended Text Generation with Dynamic Knowledge Triples. In Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023), pages 3189–3203.

Zhiyang Zhang, Yaping Zhang, Yupu Liang, Lu Xiang, Yang Zhao, Yu Zhou, and Chengqing Zong. 2023. LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder. In Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023), pages 10043–10053.

Rongchuan Tang, Yang Zhao, Chengqing Zong, and Yu Zhou. 2023. Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), pages 10508–10519.

Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong (2023). E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation. In Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR 2023).

Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong (2023). Multi-Teacher Knowledge Distillation For Text Image Machine Translation. In Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR 2023).

Zhiyang Zhang, Yaping Zhang, Lu Xiang, Yang Zhao, Yu Zhou. A Novel Dataset and Benchmark Analysis on Document Image Translation. : In Proceedings of the 19th China Conference on Machine Translation (CCMT 2023) (Best paper award).

–2022

Xiaomian Kang, Yang Zhao, Jiajun Zhang, Chengqing Zong (2022). Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation. ACM Transactions on Asian and Low-Resource Language Information Processing, 21, 3, Article 59 (May 2022), 21 pages. https://doi.org/10.1145/3485469.

Yang Zhao, Junnan Zhu, Lu Xiang, Jiajun Zhang, Yu Zhou, Feifei Zhai, Chengqing Zong. 2022. Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation. arXiv preprint arXiv:2212.02800.

Cong Ma, Yaping Zhang, Mei Tu, Xu Han, Linghui Wu, Yang Zhao, Yu Zhou. 2022. Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task. In Proceedings of the 26TH International Conference on Pattern Recognition (ICPR 2022).

–2021

Journal

Mei Li, Lu Xiang, Xiaomian Kang, Yang Zhao, Yu Zhou, Chengqing Zong (2021). Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer. IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 3362-3374, 2021, doi: 10.1109/TASLP.2021.3122301.

Lu Xiang, Junnan Zhu, Yang Zhao, Yu Zhou, Chengqing Zong (2021). Robust cross-lingual task-oriented dialogue. ACM Transactions on Asian and Low-Resource Language Information Processing, 20, 6, Article 93 (November 2021), 24 pages. https://doi.org/10.1145/3457571

Conference

Hao He, Qian Wang, Zhipeng Yu, Yang Zhao, Jiajun Zhang, Chengqing Zong (2021). Synchronous interactive decoding for multilingual neural machine translation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAA 2021), 35(14), 12981-12988. https://doi.org/10.1609/aaai.v35i14.17535

Lu Xiang, Yang Zhao, Junnan Zhu, Yu Zhou, Chengqing Zong (2021). Zero-Shot Deployment for Cross-Lingual Dialogue System. In CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2021) . vol 13029. Springer. https://doi.org/10.1007/978-3-030-88483-3_15.

–2020

Journal

Jiajun Zhang, Long Zhou, Yang Zhao, Chengqing Zong. 2020. Synchronous bidirectional inference for neural sequence generation. Artificial Intelligence, Volume 281, 2020, 103234, ISSN 0004-3702, https://doi.org/10.1016/j.artint.2020.103234.

Feng Wang, Juan Du, Yang Zhao, Tao Tang, Jianjun Shi. 2020. A deep learning based data fusion method for degradation modeling and prognostics. IEEE Transactions on Reliability. vol. 70, no. 2, pp. 775-789, June 2021, doi: 10.1109/TR.2020.3011500.

Conference

Yang Zhao, Jiajun Zhang, Yu Zhou, Chengqing Zong. 2020. Knowledge graphs enhanced neural machine translation. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (IJCAI 2020). Article 559, 4039–4045.

Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang, Yu Zhou, Chengqing Zong. 2020. Knowledge graph enhanced neural machine translation via multi-task learning on sub-entity granularity. In Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), pages 4495–4505, Barcelona, Spain (Online). International Committee on Computational Linguistics.

Xiaomian Kang, Yang Zhao, Jiajun Zhang, Chengqing Zong. 2020. Dynamic context selection for document-level neural machine translation via reinforcement learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), pages 2242–2254, Online. Association for Computational Linguistics.

Long Zhou, Jiajun Zhang, Yang Zhao, Chengqing Zong. 2020. Non-autoregressive neural machine translation with distortion model. In CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020). vol 12430. Springer. https://doi.org/10.1007/978-3-030-60450-9_32.

Qian Wang, Yuchen Liu, Cong Ma, Yu Lu, Yining Wang, Long Zhou, Yang Zhao, Jiajun Zhang, Chengqing Zong. 2020. CASIA’s System for IWSLT 2020 Open Domain Translation. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 130–139, Online. Association for Computational Linguistics.

–2019

Yang Zhao, Jiajun Zhang, Chengqing Zong, Zhongjun He, Hua Wu. 2019. Addressing the under-translation problem from the entropy perspective. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2019), 33(01), 451-458. https://doi.org/10.1609/aaai.v33i01.3301451

–2018

Journal

Jiajun Zhang, Yang Zhao, Haoran Li, Chengqing Zong. 2018. Attention with sparsity regularization for neural machine translation and summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 3, pp. 507-518, March 2019, doi: 10.1109/TASLP.2018.2883740.

Conference

Yang Zhao, Jiajun Zhang, Zhongjun He, Chengqing Zong, Hua Wu. 2018. Addressing troublesome words in neural machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), pages 391–400, Brussels, Belgium. Association for Computational Linguistics.

Yang Zhao, Yining Wang, Jiajun Zhang, Chengqing Zong. 2018. Phrase table as recommendation memory for neural machine translation. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), AAAI Press, 4609–4615.

Yang Zhao, Jiajun Zhang and Chengqing Zong. 2018. Exploiting pre-ordering for neural machine translation. In Proceedings of the eleventh international conference on language resources and evaluation (lrec 2018), pages 893–899.

Yuchen Liu, Long Zhou, Yining Wang, Yang Zhao, Jiajun Zhang, and Chengqing Zong. 2018. A comparable study on model averaging, ensembling and reranking in nmt. In CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2018). vol 11109. Springer. https://doi.org/10.1007/978-3-319-99501-4_26.

–Before 2018

Yang Zhao, Yining Wang, Jiajun Zhang, and Chengqing Zong. 2017. Cost-aware learning rate for neural machine translation. Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data (CCL 2017), vol 10565. Springer. https://doi.org/10.1007/978-3-319-69005-6_8

Yining Wang, Yang Zhao, Jiajun Zhang, Chengqing Zong, and Zhengshan Xue. 2017. Towards Neural Machine Translation with Partially Aligned Corpora. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP 2017), pages 384–393, Taipei, Taiwan. Asian Federation of Natural Language Processing.

Yang Zhao, Tian-hua Xu, Hai-feng Wang. 2015. Text mining based fault diagnosis of vehicle on-board equipment for high speed railway. In Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC 2015).

（1） Vector Quantization Knowledge Transfer For End-to-end text image machine translation, 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2024, 第 3 作者
（2） Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling, The 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024), 2024, 第 5 作者
（3） Born a BabNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation, The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, 第 5 作者
（4） Transformer: A General Framework from Machine Translation to Others., Machine Intelligence Research, 2023, 第 1 作者
（5） Zero-shot language extension for dialogue state tracking via pre-trained models and multi-auxiliary-tasks fine-tuning, Knowledge-Based Systems, 2023, 第 2 作者
（6） Modal Contrastive Learning based End-to-End Text Image Machine Translation, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023, 第 5 作者
（7） CCIM: Cross-modal Cross-lingual Interactive Image Translation, Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023), 2023, 第 4 作者
（8） Towards Informative Open-ended Text Generation with Dynamic Knowledge Triples, Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023),, 2023, 第 2 作者
（9） E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation, Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR 2023), 2023, 第 4 作者
（10） Multi-Teacher Knowledge Distillation For Text Image Machine Translation, Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR 2023), 2023, 第 4 作者
（11） LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder, Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, 第 5 作者
（12） Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), 2023, 第 2 作者
（13） Zero-shot language extension for dialogue state tracking via pre-trained models and multi-auxiliary-tasks fine-tuning, KNOWLEDGE-BASED SYSTEMS, 2023, 第 2 作者
（14） Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention, he 61st Annual Meeting of the Association for Computational Linguistics (ACL2023), 2023, 第 2 作者
（15） ChatGPT 能力分析与未来展望, 中国科学基金, 2023, 第 2 作者
（16） Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation, ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2022, 第 2 作者
（17） Robust Cross-lingual Task-oriented Dialogue, ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2021, 第 3 作者
（18） Knowledge graphs enhanced neural machine translation, Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (IJCAI 2020), 2020, 第 1 作者
（19） Knowledge graph enhanced neural machine translation via multi-task learning on sub-entity granularity, Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020, 第 1 作者
（20） CASIA���s System for IWSLT 2020 Open Domain Translation, 17TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE TRANSLATION (IWSLT 2020), 2020, 第 7 作者
（21） Synchronous bidirectional inference for neural sequence generation, ARTIFICIAL INTELLIGENCE, 2020, 第 3 作者
（22） Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning, 2020, 第 2 作者
（23） Addressing the under-translation problem from the entropy perspective, Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2019), 2019, 第 1 作者
（24） 民汉稀缺资源神经机器翻译技术研究, The Study on Ethnic-to-Chinese Scare-Resource Neural Machine Translation, 江西师范大学学报:自然科学版, 2019, 第 1 作者
（25） Attention with sparsity regularization for neural machine translation and summarization, IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 第 2 作者
（26） Addressing the Under-translation Problem from the Entropy Perspective, 2019, 第 5 作者
（27） Phrase table as recommendation memory for neural machine translation, Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), 2018, 第 1 作者
（28） Addressing troublesome words in neural machine translation, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), 2018, 第 1 作者
（29） Addressing Troublesome Words in Neural Machine Translation, 2018, 第 4 作者
（30） Phrase Table as Recommendation Memory for Neural Machine Translation, 2018, 第 1 作者
（31） Exploiting Pre-Ordering for Neural Machine Translation, 2018, 第 2 作者
（32） Cost-aware Learning Rate for Neural Machine Translation, 2017, 第 4 作者
（33） Towards Neural Machine Translation with Partially Aligned Corpora, 2017, 第 1 作者
（34） Zero-shot language extension for dialogue state tracking via pre-trained models and multi-auxiliary-tasks fine-tuning, KNOWLEDGE-BASED SYSTEMS, 第 2 作者