Update README.md

README.md

@@ -1,4 +1,4 @@
-# Twitter-roBERTa-base
+# Twitter-roBERTa-base for Offensive Language Identification
 
 This is a roBERTa-base model trained on ~58M tweets and finetuned for the Offensive Language Identification task at Semeval 2019. 
 For full description: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). 
@@ -15,6 +15,15 @@ from scipy.special import softmax
 import csv
 import urllib.request
 
+# Preprocess text (username and link placeholders)
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    return " ".join(new_text)
+
 # Tasks:
 # emoji, emotion, hate, irony, offensive, sentiment
 # stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
@@ -37,6 +46,7 @@ model = AutoModelForSequenceClassification.from_pretrained(MODEL)
 model.save_pretrained(MODEL)
 
 text = "Good night 😊"
+text = preprocess(text)
 encoded_input = tokenizer(text, return_tensors='pt')
 output = model(**encoded_input)
 scores = output[0][0].detach().numpy()