diff --git a/README.md b/README.md
index ea4fd5c..1be05bb 100644
--- a/README.md
+++ b/README.md
@@ -2,9 +2,15 @@
 
 This is a roBERTa-base model trained on ~58M tweets and finetuned for sentiment analysis with the TweetEval benchmark.
 
-- Paper: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). 
+- Reference Paper: [_TweetEval_ (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). 
 - Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
 
+<b>Labels</b>: 
+0 -> Negative;
+1 -> Neutral;
+2 -> Positive
+
+
 ## Example of classification
 
 ```python