Abstract: Classically, the quantization of the soft information supplied to a finite-precision decoder is chosen to optimize a certain criterion which does not depend on the characteristics of the ...
This repository contains the source code for our TACL paper "Controllable Summarization with Constrained Markov Decision Process". ML training for D.GPT2 model on CNN/DM. python3 -m ...
Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback