Closed kastein closed 1 year ago
Mistakes when creating the input string for the model in generate.py.
about 1. context is first a list but should be joined then into a string -> see the read_document function in dataset_reader.py but this function is not called in the generate_recipe.py script
about 2. In the recipe-generation-model inference code, the AMRs are read using the read_data_set function from dataset_reader.py. In the current repository, the AMRs are read using the read_aligned_amr_file function from action_amr_graph_mappings and get then transformed to strings
Many recipes generated using the generate.py script include repetitions of complete instructions or instructions following each other start with the same tokens.
For example for cauliflower_mash_5.conllu (not part of the training set of the model):
In contrast to this, the recipe generated from the same model for the same amr graphs using the scripts in the recipe-generation-model repository looks much better:
TODO: figure out where this difference comes from