Hi guys, I've completed the training and validations and tests with the preprocessed dataset a few days ago. However my mentor ordered me to test this model on the DUC-2004 dataset. I'm not sure how to process the dataset just for testing, so I followed the guides in README.md and stuck at this step:
Step 4. Format to Simpler Json Files python preprocess.py -mode format_to_lines -raw_path RAW_PATH -save_path JSON_PATH -map_path MAP_PATH -lower
Below is part of the output of Step 3 and the command I used in step 4
As you can see, no output was printed in step 4. I doubt that's because of the /urls folder. I don't know how to process the files in it to match with my dataset.
Moreover, my merged_story_tokenized files look like this
Can someone please help me? Or show me the way to process the data, just for testing?
Hi guys, I've completed the training and validations and tests with the preprocessed dataset a few days ago. However my mentor ordered me to test this model on the DUC-2004 dataset. I'm not sure how to process the dataset just for testing, so I followed the guides in README.md and stuck at this step:
As you can see, no output was printed in step 4. I doubt that's because of the /urls folder. I don't know how to process the files in it to match with my dataset.
Moreover, my merged_story_tokenized files look like this
Can someone please help me? Or show me the way to process the data, just for testing?
Step 4. Format to Simpler Json Files python preprocess.py -mode format_to_lines -raw_path RAW_PATH -save_path JSON_PATH -map_path MAP_PATH -lowerBelow is part of the output of Step 3 and the command I used in step 4