a-PyTorch-Tutorial-to-Sequence-Labeling
a-PyTorch-Tutorial-to-Sequence-Labeling copied to clipboard
inquiry in log-sum-exp(all scores) - gold score
Hi, Thanks for the great explanation. I am wondering if I want to calculate partial CRF (http://aclweb.org/anthology/C18-1183)where we have some gold tag for some token and all possible tags for other tokens and it needs to calculate the following formula? log_sum_ex (all socore) - log_sum_ex(partial score) what would be the changes in the code?
Thanks
I found a way to calculate partial CRF, however I made it with another CRF layer implementation. Your CRF layer implementation is so fast, however it is not compatible in a way to apply fuzzy/partial CRF!