米成刚

博士、副教授

研究方向：自然语言处理，机器翻译

电子邮箱： michenggang@gmail.com

个人简介：

米成刚，博士、副教授。2010年7月毕业于西安邮电学院软件工程专业，获工学学士学位。2015年7月毕业于中国科学院大学计算机应用技术专业，获工学博士学位。2015年7月至2018年9月在中国科学院新疆理化技术研究所任助理研究员。2018年10月至2021年11月在西北工业大学计算机学院从事博士后研究。近五年来，在本领域学术期刊及会议（包括 COLING，ACM TALLIP，IEEE TETCI，Machine Translation)发表论文20余篇。主持国家自然科学基金青年基金1项，主持中国科学院“西部青年学者”B类项目1项。参与国家重点研发计划、科技部重大专项、国家自然科学基金重点项目等。

科学研究：

一、发表学术论文

（1）期刊论文

[1] Chenggang Mi. Improving the Robustness of Loanword Identification in Social Media Texts. ACM Transactions on Asian and Low-Resource Language Information Processing. 22, 4, Article 101 (April 2023), 19 pages. https://doi.org/10.1145/3572773 (SCI)(CCF C) 

[2] Chenggang Mi. Loanword identification based on web resources: A case study on wikipedia. Computer Speech & Language. Vol 81 (March 2023). https://doi.org/10.1016/j.csl.2023.101517 (SCI)(CCF C)

[3] Chenggang Mi, Lei Xie and Yanning Zhang. Improving data augmentation for low resource speech-to-text translation with diverse paraphrasing[J]. Neural Networks, 2022, 148: 194-205. (SCI)(CCF B)

[4] Chenggang Mi, Lei Xie and Yanning Zhang. Loanword Identification in Low-resource Languages with Minimal Supervision. In ACM Transactions on Asian and Low-Resource Language Information Processing, 2020. (SCI)(CCF C)

[5] Chenggang Mi, Lei Xie and Yanning Zhang. Improving Adversarial Neural Machine Translation for Morphologically Rich Language. In IEEE Transactions on Emerging Topics in Computational Intelligence, 2020. (SCI)

[6] Zhu, S., Mi, C.(*), Li, T. et al. Improving bilingual word embeddings mapping with monolingual context information. Machine Translation (2021). (EI)(CCF C)

（2）会议论文

[1] Chenggang Mi, Shaolin Zhu, Yi Fan and Lei Xie. Incorporating Typological Features into Language Selection for Multilingual Neural Machine Translation. In APWeb-WAIM 2021: Proceedings of the 5th APWeb-WAIM International Joint Conference on Web and Big Data, Guangzhou, China, August 23-25, 2021. (CCF C)

[2] Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou and Tonghai Jiang. Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings. In COLING 2018: Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA, August 20-26, 2018. (CCF B)

[3] Chenggang Mi, Yating Yang, Xi Zhou, LeiWang and Tonghai Jiang. Improved Spoken Uyghur Segmentation for Neural Machine Translation. In ICTAI 2018: Proceedings of the 30th International Conference on Tools with Artificial Intelligence, Volos, Greece, November 5-7, 2018. (CCF C)

[4] Shaolin Zhu, Chenggang Mi (*), and Xiayang Shi. An explainable evaluation of unsupervised transfer learning for parallel sentences mining. In APWeb-WAIM 2021: Proceedings of the 5th APWeb-WAIM International Joint Conference on Web and Big Data, Guangzhou, China, August 23-25, 2021. (CCF C)

[5] Shaolin Zhu, Chenggang Mi (*), and Linlin Zhang. Inducing bilingual word representations for non-isomorphic spaces by an unsupervised way. In KSEM 2021: Proceedings of the 14th International Conference on Knowledge Science, Engineering and Management, KSEM 2021. (CCF C)

二、主持项目

[1] 国家自然科学基金青年基金：“面向低资源语言神经网络机器翻译的知识迁移方法研究”（2020.01-2022.12）；

[2] 中国科学院“西部青年学者”B类项目:“面向维汉机器翻译的双语联合切分模型研究”（2015.09-2019.08）。