Hugging Face's logo

Spaces:
amsterdamNLP
/
contrastive-pairs
Sleeping

App Files Community
Martijn van Beers commited on
Commit
a80ec68
•
1 Parent(s): cc68b4d

Use subheadings

Browse files

Use level 3 headings so they aren't as big as the title

Files changed (2) hide show
  1. notice.md +1 -1
  2. results.md +1 -1
notice.md CHANGED
@@ -1,4 +1,4 @@
1
- # Measuring bias in language models is hard!
2
  How to measure bias in language models is not trivial and still an active area of research.
3
  First of all, what is bias? As you may have noticed, stereotypes may change across languages and cultures.
4
  What is problematic in the USA, may not be relevant in the Netherlands---each cultural context requires its own careful evaluation.
 
1
+ ### Measuring bias in language models is hard!
2
  How to measure bias in language models is not trivial and still an active area of research.
3
  First of all, what is bias? As you may have noticed, stereotypes may change across languages and cultures.
4
  What is problematic in the USA, may not be relevant in the Netherlands---each cultural context requires its own careful evaluation.
results.md CHANGED
@@ -1,4 +1,4 @@
1
- # Results for French and English language models
2
  BERT is another popular type of language model, and CrowS-Pairs has originally been designed for BERT instead of GPT-2.
3
  Here you can find the results for two languages, English and French, from the authors of [the extended version of CrowS-Pairs](https://aclanthology.org/2022.acl-long.583.pdf):
4
 
 
1
+ ### Results for French and English language models
2
  BERT is another popular type of language model, and CrowS-Pairs has originally been designed for BERT instead of GPT-2.
3
  Here you can find the results for two languages, English and French, from the authors of [the extended version of CrowS-Pairs](https://aclanthology.org/2022.acl-long.583.pdf):
4