how can i use it to do text summarization? about control-length

[takase]

The description is here: https://github.com/takase/control-length/tree/master/encdec
Your question means you need more details?

[loongriver]

yes,I don't quite understand what's going on

[takase]

I think you can reproduce our results based on the description: https://github.com/takase/control-length/tree/master/encdec
If you have not run fairseq, description in fairseq (https://github.com/pytorch/fairseq/tree/master/examples/translation) might help because our code is based on fairseq.
If you have any question, can you tell me the details of the question.

[prince12th]

Maybe you can provide more details about the format of input data

[takase]

Sorry for late reply.
I add format of an input data: https://github.com/takase/control-length/tree/master/encdec .
Actually, my code regards plain text as an input for pre-processing script in the same as fairseq.