-
Notifications
You must be signed in to change notification settings - Fork 59
add base classifier and global ngrams feature functions #10
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
Conversation
webstruct/crfsuite.py
Outdated
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.
why isn't warning issued here if parsing of bigram features is not supported?
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.
since label bigram is supported by CRFsuite.
|
Hey @tpeng, CRFsuite support is great!
|
|
Hi @kmike, they are all related. for 1./3. we use CRF++ template to expand the features with for 2. since |
add a default features set for CRFsuite which demostrate how to create bigram/trigram features with python rather than template.
|
as discussed with @kmike , we decided abandon CRF++ template support. this way we can use the variable features which only supported by CRFsuite. numeric features also supported if the feature function return a tuple like (value, scale) |
webstruct/features/token_features.py
Outdated
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.
That's a lot of code duplication. I think this function should call num_pattern, or they both should call another function.
a later PR will add crfsuite base on the newly python-crfsuite(https://github.com/tpeng/python-crfsuite)
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 would be a good optional feature.
add base classifier and global ngrams feature functions
add CRFsuite backend base on the crfsuite's SWIG python package.