search

kajyuuen / Incomplete-NER-Methods

Implementation of Fuzzy-LSTM-CRF and LSTM-CRF for sequence labeling.
9 stars 0 forks source link

Experimental Results #1

Open WaNePr opened 5 years ago

WaNePr commented 5 years ago

Will it possible if you could add the experimental results you obtained in the current implementation ? e.g. a table shows the comparison between baselines and the 'hard-method'.

Many thanks

kajyuuen commented 5 years ago

Thanks, WaNePr. I agree with that opinion. But it is a bit difficult to accurately reproduce Jie's experiment that randomly removes the annotations. Please let me know if you have an idea that reproduces hard methods.