mBART
PulseAugur coverage of mBART — every cluster mentioning mBART across labs, papers, and developer communities, ranked by signal.
-
New study benchmarks machine transliteration models for Tajik-Farsi languages
This paper introduces a new benchmark for machine transliteration between Tajik and Farsi, developing a unique parallel corpus from diverse sources. The study compares six model architectures, including rule-based syste…
-
New dataset and benchmark advance Bangla text-to-gloss translation for BdSL
Researchers have developed the first dataset and benchmark for Bangla text-to-gloss translation, addressing a significant gap for the Bangla Sign Language (BdSL) community. The dataset includes manually annotated and sy…
-
CRAFT method speeds up training data selection for sequence-to-sequence models
Researchers have developed a new method called CRAFT (Clustered Regression for Adaptive Filtering of Training data) to efficiently select high-quality subsets of training data for sequence-to-sequence models. This appro…