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
Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared task
Melissa Ailem, Jinghsu Liu, Raheel Qader
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
Jian Yang, Shuming Ma, Haoyang Huang, Dongdong Zhang, Li Dong, Shaohan Huang, Alexandre Muzio, Saksham Singhal, Hany Hassan Awadalla, Xia Song, Furu Wei