GAND is a new 5,047-sentence natural benchmark of English sentences with ambiguous referent gender; contrastive saliency analysis of a 1,000-sentence subset shows MT models favor masculine forms and attend to nearby content words.
Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the G e NTE Corpus
1 Pith paper cite this work, alongside 3 external citations. Polarity classification is still indexing.
1
Pith paper citing it
3
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attribution
GAND is a new 5,047-sentence natural benchmark of English sentences with ambiguous referent gender; contrastive saliency analysis of a 1,000-sentence subset shows MT models favor masculine forms and attend to nearby content words.