BARTScore
BARTScore copied to clipboard
neulab
BARTScore: Evaluating Generated Text as Text Generation
In Table-4 in the paper, for summEval dataset you have measured COH, FAC, FLU, INFO. I wanted to know which variants of bart-score you used. From my understanding of the...
PyPi?
Hello I was wondering whether you were planning to make the library pip installable. That would make further integration a lot easier. Inspiration may be taken from [BERTScore's implementation](https://github.com/Tiiiger/bert_score). Thanks
Hi (: Great work with this paper! I was wondering if you could provide me with some additional feedback on the dataset you used for MT. If I understand correctly,...
I am trying to create the environment using the requirements.txt file. Giving the following error at matplotlib. Any idea on how to resolve this? Collecting numpy==1.18.5 (from -r requirements.txt (line...
Thanks for your nice work, I have a short question: I noticed both prompt mechanisms(prefix_prompt and suffix_prompt) were used in all three tasks. So my question is which one is...
Hi, I'm sorry if this question is kind of basic, but I do not know how to install bart_score into Jupyter Notebook. I have seen there is a bart_score.pth file...
in the bart_score.py, there is only reference based method, but no src to hyp
I went through the analysis script for comparing 2 evaluation metric wrt human evaluation (meta evaluating evaluation metric). I wanted to know if there is some way to compare 2...
I notice the result reported in Table 4 about SummEval is not the same as in the original paper. For example, the Rouge-1 of COH is 0.2500 in the original...
I noticed that in your work, you reported Kendall's Tau coefficients for different metrics on the WMT19 dataset, Spearman coefficients for the text summarization dataset, and Pearson coefficients for the...
