A post-hoc framework using fertility and entropy from word alignments on reference translations shows context redistributes responsibility to context tokens for function words but not content words across three language pairs.
BlonDe : An Automatic Evaluation Metric for Document-level Machine Translation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Human readers prefer human literary translations over AI-generated ones for immersion and clarity despite finding MT adequate and struggling to identify the source.
A literature survey that organizes prompting, fine-tuning, preference optimization, and context-aware techniques for LLM-based machine translation with emphasis on low-resource languages.
citing papers explorer
-
Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy
A post-hoc framework using fertility and entropy from word alignments on reference translations shows context redistributes responsibility to context tokens for function words but not content words across three language pairs.
-
AI translation of literary texts is "fine", but readers still prefer human translations
Human readers prefer human literary translations over AI-generated ones for immersion and clarity despite finding MT adequate and struggling to identify the source.