Yang Liu
Yang Liu
Hi @Santosh-Gupta, The format_to_lines function is specially designed for the CNNDM dataset, where it has @highlight symbols and url mappings. It makes no sense with your own data. Again, I...
Hi @tanmaypandey7, Now, this code does not do what you want. But you can just use some fake reference summaries. To run format_to_bert, please format your data as the sample...
why could not run step 5 in readme? this function is not designed to be used as an api.
chu_liu_edmounds is a broken function that I forgot to remove, in the experiments I use the MSTParser(https://github.com/travisbrown/mstparser) to get the top tree from the attention weights.
I think it can if you modify the code for function 'chuLiuEdmonds', or you can use https://github.com/sammthomson/ChuLiuEdmonds this implementation for CLE algorithm
This is indeed a bug, I have pushed a update to fix this. Sorry for this.
1. equation 16 has a typo, where it should be used with \hat(a) not a. 2. you can think a and b as scores and values, which do appear in...
Please paste your training commands here
With only 1 gpu for training, you need to accumulate the gradient for a much larger step, or the model cannot be trained effectively.
You can use our Trained Models.