g8a9 commited on
Commit
59ef0dd
1 Parent(s): 5728752

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -30,7 +30,7 @@ We trained a total of three versions for Italian and English.
30
  | Model | Download |
31
  | ------ | -------------------------|
32
  | `bert-base-uncased-ear-misogyny` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny) |
33
- | `bert-base-uncased-ear-mlma` | [Link]() |
34
  | `bert-base-uncased-ear-misogyny-italian` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny-italian) |
35
 
36
  # Authors
@@ -64,7 +64,8 @@ Please use the following BibTeX entry if you use this model in your project:
64
 
65
  # Limitations
66
 
67
- Entropy-Attention Regularization mitigates lexical overfitting but does not completely remove it. We expect the model still to show biases, e.g., peculiar keywords that induce a specific prediction regardless of the context. \
 
68
  Please refer to our paper for a quantitative evaluation of this mitigation.
69
 
70
  ## License
 
30
  | Model | Download |
31
  | ------ | -------------------------|
32
  | `bert-base-uncased-ear-misogyny` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny) |
33
+ | `bert-base-uncased-ear-mlma` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-mlma) |
34
  | `bert-base-uncased-ear-misogyny-italian` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny-italian) |
35
 
36
  # Authors
 
64
 
65
  # Limitations
66
 
67
+ Entropy-Attention Regularization mitigates lexical overfitting but does not completely remove it. We expect the model still to show biases, e.g., peculiar keywords that induce a specific prediction regardless of the context.
68
+
69
  Please refer to our paper for a quantitative evaluation of this mitigation.
70
 
71
  ## License