Sharan Narasimhan

adding scripts and tests for naturalness metric

2

PR for feature addition related to issue [129](https://github.com/Maluuba/nlg-eval/issues/129). **Motivation:** In Summarization, Generation, and Style Transfer Tasks, it is also useful to check the Fluency/ Coherence of the generated outputs (references...

Possible error in Terminology

2

It says Supervised (Parallel Data) and Unsupervised (Non-Parallel Data). I think working with labels in non-parallel datasets should also come under "supervised", as strictly speaking, we ARE using labels. Unsupervised...

This is for all people who are trying to replicate this paper in pytorch. This repo is hopelessly broken, even after fixing all bugs there are still severe implementation oversights...

If possible can you also include the code used to compute the bleu score of the model? Such as those produced to replicate the results in Figure 3 and 4...

Code wrapper used in PreConfig only works for code blocks and not inline code

2

I am using the same CodeWrapper defined in the demo doc along with PreConfig to configure light and dark colors to be used. ``` Column( crossAxisAlignment: CrossAxisAlignment.start, children: MarkdownGenerator().buildWidgets( config:...

Training is very slow on Intel Xeon 2.3Ghz, CUDA not working

1

I am using a google collab VM with an Nvidia K80 GPU and Intel Xeon CPU. On running python3 main.py, training is occurring but seems to be very slow. It...