LayoutLM
LayoutLM is a simple but effective multi-modal pre-training method of text, layout, and image for visually-rich document understanding and information extraction tasks, such as form understanding and receipt understanding. LayoutLM archives the SOTA results on…
Three mysteries in deep learning: Ensemble, knowledge distillation, and self-distillation
Under now-standard techniques, such as over-parameterization, batch-normalization, and adding residual links, “modern age” neural network training—at least for image classification tasks and many others—is usually quite stable. Using standard neural network architectures and training algorithms…
ezPitch: Connecting Salespersons and Customers through Relevant News
The goal of ezPitch is connecting salespersons and customers through relevant news. Why is this important? In the daily work, the sales persons need to search, track and explore the related news about customers before…