Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

p/r definitions

This commit is contained in:
svlandeg 2020-08-17 15:02:39 +02:00
parent 6b6f7f3e73
commit 961e818be6
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
website/docs/usage/training.md
View File

@ -430,13 +430,11 @@ components are weighted equally.
<Accordion title="Understanding the training output and score types" spaced> <Accordion title="Understanding the training output and score types" spaced>
<!-- TODO: come up with good short explanation of precision and recall -->
| Name | Description | | Name | Description |
| -------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | -------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| **Loss** | The training loss representing the amount of work left for the optimizer. Should decrease, but usually not to `0`. | | **Loss** | The training loss representing the amount of work left for the optimizer. Should decrease, but usually not to `0`. |
| **Precision** (P) | Should increase. | | **Precision** (P) | The percentage of generated predictions that are correct. Should increase. |
| **Recall** (R) | Should increase. | | **Recall** (R) | The percentage of gold-standard annotations that are in fact predicted. Should increase. |
| **F-Score** (F) | The weighted average of precision and recall. Should increase. | | **F-Score** (F) | The weighted average of precision and recall. Should increase. |
| **UAS** / **LAS** | Unlabeled and labeled attachment score for the dependency parser, i.e. the percentage of correct arcs. Should increase. | | **UAS** / **LAS** | Unlabeled and labeled attachment score for the dependency parser, i.e. the percentage of correct arcs. Should increase. |
| **Words per second** (WPS) | Prediction speed in words per second. Should stay stable. | | **Words per second** (WPS) | Prediction speed in words per second. Should stay stable. |