A problem while using

[Ricardokevins]

Awesome Work~~

While using the implement in Repo, I have a question to comfirm:

BARTScore use generate loss as the score to estimate the quality of sentence.
In bart_score.score's implement, I notice the code under:

curr_score_list = [-x.item() for x in loss]

The returned ScoreList contains some negetive value.
if SummaryA get score -1 while SummaryB get Score -100
Does that means SummaryA is better than summaryB ? (becase the loss has been Negated?, loss1 is smaller than loss100)
appreciate any reply ~

[yyy-Apple]

Since we are using the average log-likelihood for target tokens, the values should be smaller than 0 (since the probability is between 0 and 1, so the log of it should be negative).

The higher the log-likelihood, the higher the probability, so the answer to your question is yes.

[Ricardokevins]

Since we are using the average log-likelihood for target tokens, the values should be smaller than 0 (since the probability is between 0 and 1, so the log of it should be negative).

The higher the log-likelihood, the higher the probability, so the answer to your question is yes.

Thank a lot for your reply 👍 :)

[neubig]

@yyy-Apple Could we add this to README.md somewhere? This is not immediately intuitive and I think it probably deserves an explanation.

[yyy-Apple]

@yyy-Apple Could we add this to README.md somewhere? This is not immediately intuitive and I think it probably deserves an explanation.

Have added Notes on use part in README.md