Sitemap - 2022 - The Kaitchup – AI on a Budget
Run Very Large Language Models on Your Computer
How Good Is Google PaLM at Translation?
Romanize Any Language Without Machine Learning
BLEU: A Misunderstood Metric from Another Age
Why the Evaluation of OpenAI Whisper Is Not Entirely Credible
Yes, We Need Statistical Significance Testing
MBR Decoding: Get Better Results from Many Systems
A Large-Scale Automatic Evaluation of Machine Translation
compare-mt: Because Scoring Your Systems Is Not Enough
Comparing the Uncomparable to Claim the State of the Art: A Concerning Trend