A new paper proposes a revised approach to round-trip translation for evaluating machine translation systems, particularly in low-resource language scenarios. The research identifies that the copying mechanism in statistical machine translation (SMT) was a primary cause for previous discrepancies between forward and round-trip translation scores. After addressing this issue, the study demonstrates that round-trip translation can effectively predict forward translation performance without requiring reference translations, and can also enhance quality estimation models and aid in cross-system verification for shared tasks. AI
IMPACT This research could improve the evaluation of machine translation systems, especially for low-resource languages, by providing a more reliable method using round-trip translation.
RANK_REASON The item is an academic paper detailing a new methodology for machine translation evaluation. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- Rethinking Round-Trip Translation for Machine Translation Evaluation
- satisfiability modulo theories
- ScienceCast
- statistical machine translation
- Terry Yue Zhuo
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →