作者位次 #3/7ACL 2026Poster· Natural Language Processing
Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
Danlu Chen · Ka Sing He · Jiahe Tian · Chenghao Xiao · Zhaofeng Wu · Taylor Berg-Kirkpatrick · Freda Shi
摘要
The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on specific language groups—such as ancient languages—it is...