Shashi Narayan

Title info is not used.

Maybe accessing WebArxive urls are restricted! If the problem remains, drop me an email.

Here is the dataset: http://kinloch.inf.ed.ac.uk/public/XSUM-EMNLP18-Summary-Data-Original.tar.gz Please use train, development and test ids from github to split into subsets. Let me know if you have any questions.

http://kinloch.inf.ed.ac.uk/public/direct/XSUM-EMNLP18-Summary-Data-Original.tar.gz

http://bollin.inf.ed.ac.uk/public/direct/XSUM-EMNLP18-Summary-Data-Original.tar.gz

Few things to keep in mind: 1) There are some extra summary files here, you should ignore them (they have more one sentence in their summary etc). Please use the...

One way would be to use the same script to download chinese BBC articles. I have only selected English articles.

Sorry, I suppose you have to modify the script to explore wayback articles for chinese BBC articles.

In the code provided word embeddings are jointly trained. They can be initialized with pre-trained embeddings, however, I have not explored extending our model to use Bert embeddings.

Sorry for the delay. Could you please first use the original data and verify if you still get the error? http://kinloch.inf.ed.ac.uk/public/XSUM-EMNLP18-Summary-Data-Original.tar.gz