POINTER

POINTER copied to clipboard

Hi, first, thanks for your amazing work on POINTER! I am working on an application to paraphrase generation from the source sentence keywords for my PhD, but in my experience...

RaphaelChevasson

Thanks for this interesting project! Could you share the scripts for automatic evaluation?

positivepeng

Thanks for this interesting project! I am wondering: 1. Could you please share the link of the pre-training dataset (i.e. wiki data)? 2. Your paper mentioned that the sentences in...

AaronHeee

How to generate multiple samples from a group of key words using "--type sampling"

2

For a set of given key words, how to create diverse text generation like the live demo?

etrigger

Hi There, i got some Q and suggestions.

1

thanks for your code =.= 1. Q: the model faces the problem with Error Accumulation, which i suggest use '[DEL]' token to let model know when to delete which words....

wdyxwzyh

Mhzzzzz

about constructing data

3

I think there is an error at line 444 of generate_training_data.py. It should be: tokens = tokenizer.tokenize(line)

NLPCode

How to restrict some key words as a whole instead of seperating them?

2

For example, I have the following key words: Hello kitty blanket Fleece I want to treat the whole of "Hello kitty" as a key word, and generates text similar to...

etrigger

There is no check to see if the user has `conda` install on the computer in `env_setup.sh`. Hence, all the `pip install` commands inside `env_setup.sh` will install the packages in...

siv2r

slot nums

1

i didn't understand that for sequences {sos , x1, x2, ..., xt, eos}, shouldn't it be t+1 slots as described in INSERTION TRANSFORMER? which means (sos ,x1) (x1,x2),...(xt, eos), but...

wdyxwzyh