Skip to content
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

Add semeval2017 tests #83

Merged
merged 4 commits into from Feb 22, 2017
Merged

Add semeval2017 tests #83

merged 4 commits into from Feb 22, 2017

Conversation

jlowryduda
Copy link
Contributor

No description provided.


EVALS = ['men3000', 'rw', 'mturk', 'ws353', 'ws353-es', 'ws353-ro', 'gur350-de', 'zg222-de']
EVALS = ['men3000', 'rw', 'mturk', 'ws353', 'ws353-es', 'ws353-ro', 'gur350-de', 'zg222-de', 'semeval2017-monolingual',
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Stylistic nitpick: This line goes on too long. I prefer wrapping to 80 columns when that's reasonable (it is here) or 100 when the extra space is necessary.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A few other lines have the same issue.

@@ -351,6 +432,8 @@ def evaluate_raw(frame, subset='dev'):
results.loc['ws353'] = ws_score
results.loc['ws353-es'] = ws_es_score
results.loc['ws353-ro'] = ws_ro_score
results.loc['semeval2017-monolingual'] = semeval_monolingual
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we're going to need shorter labels here, as these labels are going to take up valuable space in graph legends and in string representations of Pandas tables. How about "semeval17-2a" and "semeval17-2b"?

@rspeer rspeer merged commit 098371e into master Feb 22, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants