Skip to content

feat(quality-evaluation): add overall_score field to evaluation summary. #371

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

Open
tcurek wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(quality-evaluation): add overall_score field to evaluation summary. #371

Show file tree
Hide file tree
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
11 changes: 10 additions & 1 deletion api-reference/openapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5186,6 +5186,7 @@
}
],
"summary": {
"overall_score": 72,
"granular_counts": {
"Accuracy": {
"Mistranslation": {
Expand Down Expand Up @@ -8888,10 +8889,18 @@
"summary": {
"type": "object",
"required": [
"overall_score",
"granular_counts"
],
"description": "Aggregate counts of issues across all segments.",
"description": "Aggregate quality results across all segments.",
"properties": {
"overall_score": {
"type": "integer",
"minimum": 0,
"maximum": 100,
"description": "Overall translation quality, from 0 (lowest) to 100 (highest). See [Summary](/api-reference/quality-evaluation/poll#summary).",
"example": 72
},
"granular_counts": {
"type": "object",
"description": "Nested counts keyed by `type`, then `sub_type`, then `severity`. Leaf values are integer counts.",
Expand Down
10 changes: 9 additions & 1 deletion api-reference/openapi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3520,6 +3520,7 @@ paths:
- start: 38
end: 48
summary:
overall_score: 72
granular_counts:
Accuracy:
Mistranslation:
Expand Down Expand Up @@ -6618,9 +6619,16 @@ components:
summary:
type: object
required:
- overall_score
- granular_counts
description: Aggregate counts of issues across all segments.
description: Aggregate quality results across all segments.
properties:
overall_score:
type: integer
minimum: 0
maximum: 100
description: Overall translation quality, from 0 (lowest) to 100 (highest). See [Summary](/api-reference/quality-evaluation/poll#summary).
example: 72
granular_counts:
type: object
description: Nested counts keyed by `type`, then `sub_type`, then `severity`. Leaf values are integer counts.
Expand Down
7 changes: 7 additions & 0 deletions api-reference/quality-evaluation/poll.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,13 @@ title: "Poll for the evaluation result"

See the [Quality Evaluation overview](/api-reference/quality-evaluation) for severity values, sub-types, span semantics, and limits.

### Summary

The `summary` object aggregates the results across all segments:

* `overall_score` rates the overall translation quality from 0 (lowest) to 100 (highest). The score is based on the severity of detected issues and adjusts for the length of the text, so a single issue has less impact on a longer translation than on a shorter one.
* `granular_counts` breaks down the number of issues, nested by `type`, then `sub_type`, then `severity`.

### Severity values

| **severity** | **Description** |
Expand Down
Loading