Search Results for author:
Found 2 papers, 0 papers with code
NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning
In-Context Learning (ICL) is suffering from unsatisfactory performance and under-calibration due to high prior bias and unfaithful confidence.
SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus
Therefore, to apply the pre-trained language knowledge of BERT to long text, in this paper, imitating the skimming-intensive reading method used by humans when reading a long paragraph, the Skimming-Intensive Model (SkIn) is proposed.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
