@InProceedings{yu-EtAl:2026:wmt,
  author    = {Yu, Hao  and  Chen, Ziyan  and  Zhao, Hongyu  and  Zhang, Yulong  and  Wang, Xiaogang  and  Huang, Kaiyu  and  Huang, Degen},
  title     = {TransCore: The NewTranx Submission to the Constrained Track of the WMT26 General Machine Translation Shared Task},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1484--1490},
  abstract  = {This paper describes TransCore, the NewTranx submission to the WMT26 General Machine Translation Shared Task constrained track. Our system is built upon the Qwen3-8B large language model and adopts a two-stage supervised fine-tuning framework trained exclusively on publicly available data. Our approach focuses on high-quality multilingual data construction, including parallel corpus construction, knowledge-distilled corpus construction, and instruction-following data construction. For the parallel corpus, we construct a high-quality multilingual training corpus through multilingual data collection and automatic quality filtering. For knowledge distillation, we construct a KD corpus from publicly available monolingual resources using a large language model, followed by automatic quality filtering. To support the instruction-following evaluation introduced in WMT26, we further construct instruction data covering immutable entity preservation, document-level translation, and structured translation, which are incorporated into the first-stage supervised fine-tuning. Our system participates in four language directions of the WMT26 General Machine Translation Shared Task: English$\rightarrow$Indonesian, English$\rightarrow$Kazakh, English$\rightarrow$Thai, and Chinese$\rightarrow$Japanese.},
  url       = {https://aclanthology.org/2026.wmt-1.85}
}