ComplexityMT benchmark assesses text complexity in translation

Arxiv CS.CL (NLP/language models)

The ComplexityMT benchmark assesses how text complexity and machine translation interact. It aims to standardize evaluation of complexity in translation outputs.

translation

Arxiv CS.CL (NLP/language models)·Joseph Marvin ImperialJunhong LiangBelal ShoerAbdullah BarayanRodrigo WilkensOmar MussaDawn KnightEug\'enio RibeiroEkaterina KochmarSowmya VajjalaFernando Alva-ManchegoHarish Tayyar Madabushi

6 days ago