Ting Xu

Since you mentioned, "For other datasets, we provide sample processing code which does not necessarily match the format of publicly available versions (we do not plan to adapt the code...

Hi~ I have some questions. How do you split the data for relation classification? What is the random seed for the split? Is it the same as the relation triplet...

In the paper, you mentioned that you have run five times for different data split. what's the seed for your split?

how to download treebank_3

1

When preprocessing conll05 datasets, instruction "./make_conll2005_data.sh ../data/treebank_3/" requires treebank_3 datasets, which is not available. How can I download this dataset?