rktamplayo / plansum Goto Github PK

Hi @rktamplayo , thank you for your great work!
I followed the README.md to reproduce the experimental results on Amazon dataset but encountered a few problems.

1. While running train_abstract.py in TRAIN mode, my program always exited in epoch 7-8, with loss around 3.9. The Dev ACC fluctuated between 0.2 to 0.23 within the process. Is this normal?
2. While running train_abstract.py in EVAL mode, the output seemed illogical, and quite different from the output in output/amazon/plansum.sol:
   
   As above, some irrelevant words (like tv, computer) appeared in the review summary (about cloth).
   I'd appreciate it a lot if you can help :-)

Hi @rktamplayo , thank you for your great work!
I followed the README.md to reproduce the experimental results on Amazon dataset and use the check point you released to evaluate the test.json. But I didn't get the same result as you claim in the paper and the result I got is fluctuating, which is I evaluate 5 times or more but every time I got diffrent result. I wonder that whether there is some other settings I missed.

Thank you for suggesting a good paper and code.

Can you upload the Requirements.txt required for the execution of the code?

Thank you.