diff --git a/README.md b/README.md
index 4a510ee..85ee146 100644
--- a/README.md
+++ b/README.md
@@ -62,7 +62,7 @@ The network backbone we used is EfficientNet described [here](https://arxiv.org/
 
 ##### Method description
 
-We developed a method that approximates the prediction pixels into polygons making decisions based on the whole prediction feature space. This is very different from standard approaches, e.g. the Douglas-Peucker algorithm, which are greedy in nature. The method tries to impose some of a priori building properties, which is, at the moment, manually defined and automatically tuned. Some of these a priori properties are:
+We developed a method that approximates the prediction pixels into polygons making decisions based on the whole prediction feature space. This is very different from standard approaches, e.g. the Douglas-Peucker algorithm, which are greedy in nature. The method tries to impose some of a priori building properties, which is, at the moment, manually defined and automatically tuned.
 
 ### How good is the data?