Reviews: Data Programming: Creating Large Training Sets, Quickly

This is a interesting work. The author motivates the problem regarding how availability of large labeled training sets may be hindrance to several supervised ML systems and deep learning techniques. And data programming can be an interesting approach here. Also the user study indicating how researchers find it easy to write labeling heuristics instead of generating ground truth through crowdsourcing or otherwise is a good indication of the utility of this technique. The writing is clear and easy to follow, the experiments are thorough.