Translation Task
Machine translation (MT) research focuses on automatically translating text between languages, aiming to improve accuracy, efficiency, and fluency. Current efforts concentrate on leveraging large language models (LLMs) and transformer architectures, often incorporating techniques like multilingual training, transfer learning, and data augmentation to address challenges posed by low-resource languages and diverse text types. These advancements are significantly impacting fields like cross-lingual communication, information access, and software localization, driving improvements in both the quality and accessibility of MT systems.
Papers
Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task
Keqin Bao, Yu Wan, Dayiheng Liu, Baosong Yang, Wenqiang Lei, Xiangnan He, Derek F. Wong, Jun Xie
Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task
Yu Wan, Keqin Bao, Dayiheng Liu, Baosong Yang, Derek F. Wong, Lidia S. Chao, Wenqiang Lei, Jun Xie