Golnar is going to give a talk about Graph-based Semi-supervised learning in the lab meeting this week. The meeting is on Wednesday, 1st of April, at 1:30 pm. Abstract:”Semi-supervised learning (SSL) brings the best of supervised and unsupervised learning together: it takes advantage of labelled data when available, while using information hidden in usually abundant unlabelled data. Graph-based SSL has frequently beaten other SSL approaches in the past, and has been applied to many NLP applications: POS-tagging, dependency parsing, and semantic analysis to name a few. It encourages similar data points to take similar labels even if they appear far from each other in training data (ex. across sentences). In this talk, I will cover the basics of Graph-based SSL such as graph construction, graph propagation, and inductive vs. transductive methods, while using POS-tagging as a running example task.”
