This past summer, while back at home due to COVID19, I had the fortunate opportunity to work as an applied research intern at Georgian. As the title suggests, my project was on how we can leverage the strong performance of transformers and incorporate tabular data…
Introduction Recently while running some experiments on Bert and trying to reproduce the results across different experiments with the same hyperparameters, I encountered something strange. In my two experiments, the only thing that was different was that I was evaluating the model performance on the…
Introduction In the last blog we gave a brief introduction to Graph Convolution Networks and examined the model, $\textsc{TextGCN}$, which builds a graph from word occurrences in documents and utilizes GCNs to classify documents (the nodes in the constructed graph). Likewise, with COVID-19 affecting people all over the…
Introduction There have been many interesting applications of graph structure in text data for natural language processing tasks. For a brief overview check out my other article here. In this article, I want to go more in depth into one of the papers that had…
Introduction In recent years, there has been an explosion of interest in neural networks designed for graph structured data. Graph structured data is any set of nodes connected by edges. We denote a graph as $ \mathcal{G}=(V,E) $ with node set $ V $ and…
My research experience and things I have learned and figured out along the way.