Punchwes

Hi, in the readme section, you said that the reordering has been extended to whole text flow rather than the first page. However, it seems not working on my case....

Hi, Thanks very much for releasing this excellent paraphrase generation dataset. I've got one question to ask, is your dataset bidirectional or unidirectional? Basically when you say the paraphrase holds...

Can I interpret the positive examples in PAWS as exact paraphrase?

1

Hi, Thanks very much for your work, these datasets are great for evaluation. Given many positive examples in datasets like MRPC and TwitterURL are quasi-paraphrases (similar but not the same...

install failure (Failed building wheel for python-zpar) on macOS Catalina

23

when installing python-zpar by using `pip install python-zpar` it gives ``` wget -N https://github.com/frcchang/zpar/archive/v0.7.5.tar.gz -O /tmp/zpar.tar.gz make: wget: No such file or directory make: *** [/tmp/zpar.tar.gz] Error 1 Traceback (most...

https://github.com/ShannonAI/Self_Explaining_Structures_Improve_NLP_Models/blob/d8b0511cd06964dbb23f1c4560f01996662b0b66/explain/trainer.py#L90 Hi, thanks for sharing your work. I am a little bit confused about how you calculate your final loss. In your paper, it says it should the sum but...

### Describe the issue Hi, Playing with the prompt compression, I am trying to obtain the exact probability/importance score for each word. However, it seems that LLMLingua does not save...

Hi, it seems that all links to pre-trained models are invalid now. I wonder is there any other valid links to obtain these pre-trained models? +-------------+-----------+---------+----------------------------+ | Model | Dimension...