nitikam

mteval-in-context

code for Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation

tangled

Code, data, and additional analysis for the paper Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics

WMT-Metrics-task.github.io

wmt20-metrics

wmt21-metrics-data

nitikam/tangled

Code, data, and additional analysis for the paper Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics

nitikam/mteval-in-context

code for Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation