add doc

XCRobert · Jun 26, 2018 · 769911d · 769911d
1 parent 5ca9595
commit 769911d
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -109,7 +109,7 @@ In our implementation, when the nbest=10, CharCNN+WordLSTM+CRF model built in NC
 
 7.Hyperparameter tuning:
 ========================
-You can get some tips [here](reademe/hyperparameter_tuning.md). Share your experience on your configuration and your dataset now!
+You can get some tips [here](readme/hyperparameter_tuning.md). Share your experience on your configuration and your dataset now!
 
 
 Cite: 

diff --git a/readme/hyperparameter_tuning.md b/readme/hyperparameter_tuning.md
@@ -5,4 +5,5 @@
 3. If you want to write a script to tune hyperparameters, you can use the `main_parse.py` to set hyperparameters in command line arguements
 4. `lr` needs to be carefully tuned for different structures:
     * If you run LSTM-LSTM-CRF on CONLL-2003 dataset, a good `lr` is 0.015
-    * If you run LSTM-CNN-CRF on CONLL-2003 dataset,, a good `lr` is 0.005
+    * If you run LSTM-CNN-CRF on CONLL-2003 dataset,, a good `lr` is 0.005
+    * If you run CNN-CNN-CRF on CONLL-2003 dataset, a good `lr` is 0.0015