COMETKiwi
PulseAugur coverage of COMETKiwi — every cluster mentioning COMETKiwi across labs, papers, and developer communities, ranked by signal.
-
New LocQE model improves translation quality estimation for localization
Researchers have developed a new model called LocQE designed to improve the accuracy of machine translation quality estimation, particularly in specialized domains like localization. Existing models, such as COMETKiwi, …
-
Multilingual embeddings show promise for translation error detection
A new study published on arXiv evaluates the effectiveness of multilingual sentence embeddings in detecting translation errors between English and Greek. Researchers developed a dataset of 1,850 examples, categorizing e…
-
KletterMix dataset boosts German language model pretraining
Researchers have developed KletterMix, a new high-quality German pretraining dataset for language models. This corpus was created by translating a state-of-the-art English pretraining dataset into German, carefully pres…