Because seq2rel needs the "special" tokens and the relation classes used in serialization, the preprocess command in this repo should save this information somewhere along with the preprocessed data. Perhaps in a JSON file in the same directory as the preprocessed data.
Because seq2rel needs the "special" tokens and the relation classes used in serialization, the
preprocess
command in this repo should save this information somewhere along with the preprocessed data. Perhaps in aJSON
file in the same directory as the preprocessed data.