Spaces:

hpi-dhc
/

FairEval

Runtime error

App Files Files Community

illorca commited on Dec 18, 2022

Commit

fca6de5

1 Parent(s): 931a43a

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -143,14 +143,14 @@ The traditional error count is:
 And the fair count is:
-| overall               | location | miscelaneous | organization | person |
-|-----------------------|----------|--------------|--------------|--------|
-| 5104 ( - \| 90,36%)   | 1545     | 561          | 1452         | 1546   |
-| 126 (18,47% \| 2,23%) | 20       | 48           | 47           | 11     |
-| 124 (18,18% \| 2,19%) | 13       | 47           | 47           | 17     |
-| 219 (32,11% \| 3,87%) | 62       | 41           | 73           | 43     |
-| 126 (18,47% \| 2,23%) | 16       | 46           | 53           | 11     |
-| 87 (12,75% \| 1,54%)  | 32       | 13           | 41           | 1      |
 #### WNUT-17
 Computing the evaluation metrics on the results from [this model](https://huggingface.co/muhtasham/bert-small-finetuned-wnut17-ner)
@@ -179,8 +179,8 @@ While the fair count is:
 | FP           | 31 (3,6% \| 2,87%)                    | 10       | 3     | 16     | 0             | 2           | 0       |
 | FN           | 725 (84,11% \| 67,19%)                | 71       | 135   | 233    | 120           | 54          | 112     |
 | LE           | 47 (5,45% \| 4,35%)                   | 4        | 18    | 2      | 6             | 7           | 10      |
-| BE           | 30 (3,48% \| 2,78%)                   | 10       | 4     | 13     | 0             | 3           | 0       |
 | LBE          | 29 (3,36% \| 2,68%)                   | 1        | 6     | 0      | 16            | 1           | 5       |
 ## Limitations and Bias
 The metric is restricted to the input schemes admitted by seqeval. For example, the application does not support numerical

 And the fair count is:
+|-----| overall               | location | miscelaneous | organization | person |
+|-----|-----------------------:|----------:|--------------:|--------------:|--------:|
+| TP  | 5104 ( - \| 90,36%)   | 1545     | 561          | 1452         | 1546   |
+| FP  | 126 (18,47% \| 2,23%) | 20       | 48           | 47           | 11     |
+| FN  | 124 (18,18% \| 2,19%) | 13       | 47           | 47           | 17     |
+| LE  | 219 (32,11% \| 3,87%) | 62       | 41           | 73           | 43     |
+| BE  | 126 (18,47% \| 2,23%) | 16       | 46           | 53           | 11     |
+| LBE | 87 (12,75% \| 1,54%)  | 32       | 13           | 41           | 1      |
 #### WNUT-17
 Computing the evaluation metrics on the results from [this model](https://huggingface.co/muhtasham/bert-small-finetuned-wnut17-ner)
 | FP           | 31 (3,6% \| 2,87%)                    | 10       | 3     | 16     | 0             | 2           | 0       |
 | FN           | 725 (84,11% \| 67,19%)                | 71       | 135   | 233    | 120           | 54          | 112     |
 | LE           | 47 (5,45% \| 4,35%)                   | 4        | 18    | 2      | 6             | 7           | 10      |
 | LBE          | 29 (3,36% \| 2,68%)                   | 1        | 6     | 0      | 16            | 1           | 5       |
+| BE           | 30 (3,48% \| 2,78%)                   | 10       | 4     | 13     | 0             | 3           | 0       |
 ## Limitations and Bias
 The metric is restricted to the input schemes admitted by seqeval. For example, the application does not support numerical