-
Notifications
You must be signed in to change notification settings - Fork 269
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Adding HONEST score #279
Adding HONEST score #279
Conversation
The documentation is not available anymore as the PR was closed or merged. |
@lvwerra I'm getting an import error for the Any ideas? |
measurements/honest/README.md
Outdated
Example 1: Calculating HONEST without groups | ||
|
||
```python | ||
>>> honest = evaluate.load('measurements/honest', lang = 'en') |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is a config_name, not a lang
, right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
so I'm waiting for the big config to be merged so we can have different config names, including lang
.
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
Co-authored-by: helen <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks really good, thanks for adding this! Left a few minor things to clean up.
word = strip_accent(word) | ||
if word in self.words: | ||
list_score["count"] += 1 | ||
list_score[self.get_hurtlex_category(word)] += 1 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the key "count"
never occurs in self.get_hurtlex_category(word)
? Otherwise you would overwrite it here.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
no it doesn't, it's not part of the lexicon. (although I do admit it's a fragile way of implementing it -- I took it directly from the HONEST code).
removing `predicted_words`
Co-authored-by: Leandro von Werra <[email protected]>
Co-authored-by: Leandro von Werra <[email protected]>
removing pandas and nump
* Adding HONEST score * adding source of code * running make * added two modes for the score, group and no group * ran make * polishing up * ran make * updating requirements * adding unidecode to tests * Update measurements/honest/README.md Co-authored-by: helen <[email protected]> * Update measurements/honest/README.md Co-authored-by: helen <[email protected]> * Update measurements/honest/README.md Co-authored-by: helen <[email protected]> * Update measurements/honest/README.md Co-authored-by: helen <[email protected]> * Update README.md * Update measurements/honest/README.md Co-authored-by: helen <[email protected]> * Update measurements/honest/honest.py Co-authored-by: helen <[email protected]> * Update README.md * Update honest.py * Update measurements/honest/honest.py Co-authored-by: helen <[email protected]> * keeping lang as a parameter for now * fixing loading * Update honest.py removing `predicted_words` * Update measurements/honest/honest.py Co-authored-by: Leandro von Werra <[email protected]> * Update measurements/honest/honest.py Co-authored-by: Leandro von Werra <[email protected]> * Update requirements.txt removing pandas and nump * raising value error is config incorrect * Update honest.py Co-authored-by: helen <[email protected]> Co-authored-by: Leandro von Werra <[email protected]>
Adding HONEST score from https://github.com/MilaNLProc/honest