Yue Dong

Hi @jadore801120, I wonder if this could be potentially caused by the eval part mentioned in #55 ? it seems that the tgt sequence is given during validation... `def eval_epoch(model,...

Hi, this is the standard way to train the seq2seq model with teacher forcing where you would shift the input and output by one and compute the maximum log-likelihood. (please...

comp_txt, simp_txt refer to the source text and target text in the simplification task. WikiLarge, WikiSmall, and Newsela.

Hi Fernando, Sorry for the delay. This is a project I did during an internship and I have no access to the cluster at the company anymore. I will rerun...

Hi, Most of the code is in data_preprocess.py, the filtered files remove the rows where the source and the target are identical.

Hi, I think as long as you have the source and the target in txt files, you can use the data_preprocessing.py to make it into data frame and the train...

Hi, The model needs supervised training. I will retrain the model and release the pre-trained model later, which can be used for other datasets without the target.