Search papers, labs, and topics across Lattice.
University of Zurich
3
0
5
ALEE uncovers substantial performance gaps in cross-lingual semantic representation that reflect the biases of training data and tokenization strategies across 275+ languages.
RL-trained models can significantly improve unseen language translation by effectively leveraging contextual linguistic knowledge, outperforming traditional methods.
Democratizing morphological data collection for low-resource languages is now within reach thanks to a new platform that combines expert knowledge with community contributions.
