DeBERTa improves BERT-style models by separating content and relative position in attention and adding absolute positions to the decoder, yielding consistent gains on NLU and NLG tasks and the first single-model superhuman score on SuperGLUE.
InProceedings of the Thirteenth Language Resources and Evalua- tion Conference, pages 2682–2692, Marseille, France
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
CNSocialDepress is a new benchmark dataset containing 44,178 Chinese social media posts annotated by experts with binary depression risk labels and multidimensional psychological attributes for fine-grained analysis.
citing papers explorer
-
DeBERTa: Decoding-enhanced BERT with Disentangled Attention
DeBERTa improves BERT-style models by separating content and relative position in attention and adding absolute positions to the decoder, yielding consistent gains on NLU and NLG tasks and the first single-model superhuman score on SuperGLUE.
-
CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
CNSocialDepress is a new benchmark dataset containing 44,178 Chinese social media posts annotated by experts with binary depression risk labels and multidimensional psychological attributes for fine-grained analysis.