Search papers, labs, and topics across Lattice.
4
0
5
0
Machine translation benchmarks have functionally saturated, but pairing human-authored failure cases with deterministic verification rules reveals critical multimodal blind spots that automated metrics consistently miss.
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.
