Industry | 2021.08.05
769 Machine Translation Papers Show Automatic Evaluation Worsening
Combing through papers released from 2010 to 2020, researchers identify overreliance on metric BLEU to the exclusion of 100+ alternatives — a major weak point.
The post 769 Machine Translation Papers Show Automatic Evaluation Worsening appeared first on Slator .
For more information, please visit
https://slator.com/769-machine-translati[...]utomatic-evaluation-worsening/
