Thanks to visit codestin.com
Credit goes to github.com

Skip to content

fix: add bert_score_dissimilarity description #193

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 19, 2024
Merged

fix: add bert_score_dissimilarity description #193

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/fmeval/reporting/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@
DELTA_BERT_SCORE,
DELTA_METEOR_SCORE,
)
from fmeval.eval_algorithms.general_semantic_robustness import WER_SCORE
from fmeval.eval_algorithms.general_semantic_robustness import WER_SCORE, BERT_SCORE_DISSIMILARITY
from fmeval.eval_algorithms import (
TREX,
BOOLQ,
Expand Down Expand Up @@ -188,6 +188,7 @@ class ListType(Enum):
BALANCED_ACCURACY_SCORE: "The balanced accuracy score is the same as accuracy in the binary case, otherwise averaged recall per class.",
# General semantic robustness
WER_SCORE: "Word error rate (WER) is a value between 0 and 1, and measures the difference between the model output on the unperturbed input and the output(s) on one or more perturbed versions of the same input. For more details on how word error rate is computed, see the [HuggingFace Article on Word Error Rate](https://huggingface.co/spaces/evaluate-metric/wer).",
BERT_SCORE_DISSIMILARITY: "BERTScore Dissimilarity is computed as 1 - BERTScore and measures semantic differences between the original and perturbed versions of the same input.",
# Summarization semantic robustness
DELTA_ROUGE_SCORE: "Delta ROUGE-N score measures the change in Rouge between the original and perturbed versions of the same input.",
DELTA_METEOR_SCORE: "Delta Meteor score measures the change in Meteor between the original and perturbed versions of the same input.",
Expand Down