luisespinosa commited on
Commit
df3f121
1 Parent(s): e73704e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -4
README.md CHANGED
@@ -1,8 +1,9 @@
1
  # Twitter-roBERTa-base for Irony Detection
2
 
3
- This is a roBERTa-base model trained on ~58M tweets and finetuned for the Irony Detection task at Semeval 2018.
4
- For full description: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
5
- To evaluate this and other models on Twitter-specific data, please refer to the [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
 
6
 
7
  ## Example of classification
8
 
@@ -17,7 +18,8 @@ import urllib.request
17
 
18
  # Preprocess text (username and link placeholders)
19
  def preprocess(text):
20
- new_text = []
 
21
  for t in text.split(" "):
22
  t = '@user' if t.startswith('@') and len(t) > 1 else t
23
  t = 'http' if t.startswith('http') else t
 
1
  # Twitter-roBERTa-base for Irony Detection
2
 
3
+ This is a roBERTa-base model trained on ~58M tweets and finetuned for irony detection with the TweetEval benchmark.
4
+
5
+ - Paper: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
6
+ - Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
7
 
8
  ## Example of classification
9
 
 
18
 
19
  # Preprocess text (username and link placeholders)
20
  def preprocess(text):
21
+ new_text = [
22
+ ]
23
  for t in text.split(" "):
24
  t = '@user' if t.startswith('@') and len(t) > 1 else t
25
  t = 'http' if t.startswith('http') else t