Search Results for author:
Found 3 papers, 2 papers with code
Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
Based on this finding, we propose a cross-architecture training procedure with a margin focused loss (Margin-MSE), that adapts knowledge distillation to the varying score output distributions of different BERT and non-BERT passage ranking architectures.
Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering
We extend the ranked retrieval annotations of the Deep Learning track of TREC 2019 with passage and word level graded relevance annotations for all relevant documents.
Playing Pinball with non-invasive BCI
Compared to invasive Brain-Computer Interfaces (BCI), non-invasive BCI systems based on Electroencephalogram (EEG) signals have not been applied successfully for complex control tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
