Jiacheng Xu

@kalpitdixit I am implementing it in PyTorch. In pytorch, every previous occurrence is overwritten by following ones. So I preprocess the data, counting and mapping, and then when training or...

Hi all, https://utexas.app.box.com/v/DiscoBERT-ACL2020/folder/110710107654 is where I put the model configuration file. have you guys checked this folder?

Hi! Thanks for your interest. Unfortunately as far as I know there is no EDU segmenter for Chinese. If you want to run the system in Chinese or other languages,...

btw which link is unavailable? @shaofengzeng

Hi! Thanks for your suggestion. Longformer is great for the long document scenario. In this project, I can actually change the max_len to any, see https://github.com/jiacheng-xu/DiscoBERT/blob/a96922a2cfd4b14d48a38d943529f8c035b43d84/data_preparation/data_structure.py#L20 What I do is...

Thanks for your interest. please contact me through [email protected] for further assistance.

> Hi, > > I have some questions regarding the implementation, and I can't reproduce the perplexities reported in the paper. > > 1. I'd be interested in #5, as...

label_matching.py is not used I suppose. I am not 100% sure about the function of label_matching.py. It is designed for reading TREC dataset which finally is not used as our...

> Hi, sorry for asking too much.... > When I run label_matching code, I got this error. > I couldn't find which code should be run before label_matching. (I am...

Hi Lucas, thanks for your interest. I am sorry that I didn’t put all the commands on the github page because there are too many tables ( and it’s hard...