Everything you need to know about how we analyzed the 13,000+ comments submitted in the federal government’s request for ...

News: We released a more general-purpose LM-GNN reasoning framework, MHGRN, which includes more options for text/graph encoders. It also matches the current state-of-the-art performance (76.5% acc) on ...

Code is released. With better CUDA optimization, HAIS now only takes 339 ms on TITAN X, much better than the latency reported in the paper (410 ms on TITAN X). HAIS is an efficient and concise ...