Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Masaryk University
2
0
2
The illusion of plentiful Lombard data is shattered by an audit revealing severe biases and misidentifications that threaten the integrity of NLP applications.
Classifying subtle orthographic variations in low-resource languages is now possible with 96% accuracy, paving the way for more robust NLP models.