xdqkid
xdqkid
As seen in #5 , this work relies on anonymization excessively. So its performance is not good. It seems that the author is too busy, so there is no plan...
> Thank you for your reply. So, as far as I read the scripts, the following steps seems to be a way to achieve it, given the current state. Is...
> > > Thank you for your reply. So, as far as I read the scripts, the following steps seems to be a way to achieve it, given the current...
> > > > > Thank you for your reply. So, as far as I read the scripts, the following steps seems to be a way to achieve it, given...
> @xdqkid That paper's idea is very nice, but the author has not released his source code. It's hard to follow :) all right, I'm so sorry to hear that...
Thank you for following my work，i will try to put the model on other more convenient network disks in the future.
Hello, We did not do any additional operations in pre-processing ~~and post-processing~~. Notice that: 1. We use the source sentence in "amrs" in AMR2.0 instead of that in "alignment". The...
Hi, Thank you for your reminder! When we do post-processing, we do some processing on the wiki. We store the dictionary in the training set and prefer to use this...
Hi, Thanks for your advice. I'm too busy recently, e.g. looking for a job, preparing for dissertation, building websites for CCMT2020&AACL2020. I will probably find a time to push an...
How can u get so low bleu score? I do the reproduced exp & get bleu about 26 in the baseline system. Do U do something wrong in exp? like...