| Download | - View final version: Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classification (PDF, 2.9 MiB)
|
|---|
| Author | Search for: Dawkins, Hillary1; Search for: Nejadgholi, Isar1 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 60th Annual Meeting of the Association for Computational Linguistics, May 22-27, 2022, Dublin, Ireland |
|---|
| Abstract | Certainty calibration is an important goal on the path to interpretability and trustworthy AI. Particularly in the context of human-in-the-loop systems, high-quality low to mid-range certainty estimates are essential. In the presence of a dominant high-certainty class, for instance the non-entity class in NER problems, existing calibration error measures are completely insensitive to potentially large errors in this certainty region of interest. We introduce a region-balanced calibration error metric that weights all certainty regions equally. When low and mid certainty estimates are taken into account, calibration error is typically larger than previously reported. We introduce a simple extension of temperature scaling, requiring no additional computation, that can reduce both traditional and region-balanced notions of calibration error over existing baselines. |
|---|
| Publication date | 2022-05 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | f016dcbe-c78a-4297-92fc-77a8b3d4cc20 |
|---|
| Record created | 2022-06-03 |
|---|
| Record modified | 2022-06-03 |
|---|
