Matt Gardner received his Ph.D. from the Language Technologies Institute at Carnegie Mellon University in November 2015. His research interests include machine reading and reasoning, extracting information from text and using it to answer questions. At home, he likes to play harp and flute duets with his wife, read and play with his kids, and play soccer with friends.
The path ranking algorithm (PRA) and subgraph feature extraction (SFE) are algorithms that extract feature matrices from graphs. This git repository contains code implementating these two algorithms, produces matrices that are useful in a variety of situations. The repository also contains code for running experiments doing link prediction in a graph using these feature matrices (also known as knowledge base completion, when the graph corresponds to a knowledge base such as Freebase or NELL).
Using feature matrices generated from graphs (using the PRA/SFE code linked above) to answer questions, both science questions and machine-generated questions from the Facebook bAbI dataset.