Update README.md

README.md

@@ -13,24 +13,24 @@ tags:
 
 # Text-to-Attribute Understanding
 This is the text-to-attribute model to extract musical attributes from text, introduced in the paper [*MuseCoco: Generating Symbolic Music from Text*](https://arxiv.org/abs/2306.00110) and [first released in this repository](https://github.com/microsoft/muzic/tree/main/musecoco).
-It is based on BERT-large and has multiple classification heads for diverse musical attributes.
+It is based on BERT-large and has multiple classification heads for diverse musical attributes: 
 
-There is the mapping between keywords used in the model and musical attributes:
+ musical attributes:
 ```json
-{
-    "I1s2": "Instrument",
-    "R1": "Rhythm Danceability",
-    "R3": "Rhythm Intensity",
-    "S2s1": "Artist",
-    "S4": "Genre",
-    "B1s1": "Bar",
-    "TS1s1": "Time Signature",
-    "K1": "Key",
-    "T1s1": "Tempo",
-    "P4": "Pitch Range",
-    "EM1": "Emotion",
-    "TM1": "Time"
-}
+[
+    "Instrument",
+    "Rhythm Danceability",
+    "Rhythm Intensity",
+    "Artist",
+    "Genre",
+    "Bar",
+    "Time Signature",
+    "Key",
+    "Tempo",
+    "Pitch Range",
+    "Emotion",
+    "Time"
+]
 ```
 
 # BibTeX entry and citation info