add RGL README (#1936)

Author: tianxin

examples/few_shot/rgl/README.md

@@ -0,0 +1,12 @@
+# RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning
+
+The code will be released at this repository soon for our paper [RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning]().
+
+**************************** Updates ****************************
+
+2022-04-08: Our paper has been accepted to Findings of NAACL 2022!
+
+# Overview
+We propose a simple yet effective Relation Graph augmented Learning RGL method that can obtain better performance in few-shot natural language understanding tasks.
+
+RGL constructs a relation graph based on the label consistency between samples in the same batch, and learns to solve the resultant node classification and link prediction problems of the relation graphs. In this way, RGL fully exploits the limited supervised information, which can boost the tuning effectiveness.