Sebastian Martschat

Results 2 issues of Sebastian Martschat

cort currently needs a lot of RAM, predicting with the latent ranking model on the CoNLL-2012 development data takes ~8GB, mainly due to multiprocessing during feature extraction.

In the README, the following example is given: ``` ref_texts = {'A': "Poor nations pressurise developed countries into granting trade subsidies.", 'B': "Developed countries should be pressurized. Business exemptions to...