33 citations · 91 across the 12 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CL2021★ 33 cited
Macro-Average: Rare Types Are Important Too
Thamme Gowda, Weiqiu You, Constantine Lignos +1
While traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency, they struggle to reflect adequacy. Model-based MT metrics trained on seg…
cs.CL2021★ 17 cited
Many-to-English Machine Translation Tools, Data, and Pretrained Models
Thamme Gowda, Zhao Zhang, Chris A Mattmann +1
While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only on…