Individual results
View docsView in-depth performance of a single language model on a single test suite.
Region-by-region surprisal
Sample item for Reflexive Number Agreement (masculine; with subject relative clause)
The first item of the test suite is shown below for quick reference. Please visit the page for Reflexive Number Agreement (masculine; with subject relative clause) to see the full list of items.
| Item |
Condition
| intro | np_subject | that | embed_vp | the | embed_np | matrix_v | reflexive |
|---|---|---|---|---|---|---|---|---|---|
| Item | Condition | intro | np_subject | that | embed_vp | the | embed_np | matrix_v | reflexive |
| 1 | match_sing | The | author | that | liked | the | senators | hurt | himself |
| 1 | mismatch_sing | The | author | that | liked | the | senators | hurt | themselves |
| 1 | match_plural | The | authors | that | liked | the | senator | hurt | themselves |
| 1 | mismatch_plural | The | authors | that | liked | the | senator | hurt | himself |
Showing 1 to 4 of 4 entries
Prediction performance for Transformer XL on Reflexive Number Agreement (masculine; with subject relative clause)
| Accuracy |
Formula
| Description |
|---|---|---|
| Accuracy | Prediction | Description |
| 78.95% | match_plural.reflexive < mismatch_plural.reflexive |
No description provided. |
| 94.74% | match_sing.reflexive < mismatch_sing.reflexive |
No description provided. |
Showing 1 to 2 of 2 entries