Score: 3

Extending Automatic Machine Translation Evaluation to Book-Length Documents

Published: September 21, 2025 | arXiv ID: 2509.17249v1

By: Kuang-Da Wang , Shuoyang Ding , Chao-Han Huck Yang and more

BigTech Affiliations: NVIDIA

Potential Business Impact:

Tests if computers translate whole books well.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Despite Large Language Models (LLMs) demonstrating superior translation performance and long-context capabilities, evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations, token number restrictions in metrics, and rigid sentence boundary requirements. We introduce SEGALE, an evaluation scheme that extends existing automatic metrics to long-document translation by treating documents as continuous text and applying sentence segmentation and alignment methods. Our approach enables previously unattainable document-level evaluation, handling translations of arbitrary length generated with document-level prompts while accounting for under-/over-translations and varied sentence boundaries. Experiments show our scheme significantly outperforms existing long-form document evaluation schemes, while being comparable to evaluations performed with groundtruth sentence alignments. Additionally, we apply our scheme to book-length texts and newly demonstrate that many open-weight LLMs fail to effectively translate documents at their reported maximum context lengths.

Country of Origin
🇺🇸 🇹🇼 Taiwan, Province of China, United States

Repos / Data Links

Page Count
17 pages

Category
Computer Science:
Computation and Language