MERLIN
A multilingual multimodal entity linking benchmark covering five languages—Hindi, Indonesian, Japanese, Tamil, and Vietnamese—used to evaluate the cross-lingual generalization capability of entity linking systems.
Timeline (last 90 days)
MERLIN is a multilingual multimodal entity linking benchmark covering five languages: Hindi, Indonesian, Japanese, Tamil, and Vietnamese.
The framework achieves an overall accuracy improvement of 6.9% over the current state of the art on the MERLIN benchmark.
The framework achieves an accuracy improvement of up to 23.3% on rare entity slices.
All Facts (3)
MERLIN is a multilingual multimodal entity linking benchmark covering five languages: Hindi, Indonesian, Japanese, Tamil, and Vietnamese.
50%UnverifiedThe framework achieves an overall accuracy improvement of 6.9% over the current state of the art on the MERLIN benchmark.
50%UnverifiedThe framework achieves an accuracy improvement of up to 23.3% on rare entity slices.
50%