Search Results for author:
Found 3 papers, 2 papers with code
KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads
We apply KIMERA to BERT-base to evaluate the extent of the domain transfer and also improve on the already strong results of BioBERT in the clinical domain.
VisBERT: Hidden-State Visualizations for Transformers
At the same time, they are difficult to incorporate into the large, black-box models that achieve state-of-the-art results in a multitude of NLP tasks.
How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations
In order to better understand BERT and other Transformer-based models, we present a layer-wise analysis of BERT's hidden states.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
