diff --git a/README.md b/README.md
index 6caa323a2c..b5f2352fdb 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Cascade Transformer
 
-Here we provide code to reproduce our results. We provide all training data and training scripts, as well as all pretrained models used in our paper. Our code is built on top of [fairseq](https://github.com/pytorch/fairseq) and [pytorch-strcut](https://github.com/harvardnlp/pytorch-struct).
+Here we provide code to reproduce our results. We provide all training data and training scripts, as well as all pretrained models used in our paper. Our code is built on top of [fairseq](https://github.com/pytorch/fairseq) and [pytorch-struct](https://github.com/harvardnlp/pytorch-struct).
 
 ## Prerequisites