Skip to content

data(scenarii): translate 76 empty rows to English - #322

Merged
jsboige merged 2 commits into
masterfrom
data/scenarii-en-translation
May 21, 2026
Merged

data(scenarii): translate 76 empty rows to English#322
jsboige merged 2 commits into
masterfrom
data/scenarii-en-translation

Conversation

@jsboige

@jsboige jsboige commented May 21, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Translated 76 empty Scenarii rows to English using DatasetUpdater (gpt-5.5, ChunkSize=4)
  • 167/167 EN titles now complete (was 91/167)
  • Fields translated: category, subcategory, title, smoothTalker, drawer, context, issue, suggestion_en

Translation method

  • DatasetUpdater with SelectEmptyTargets=true, WriteOneTargetFileByField=true
  • Per-field CSV files merged back into source CSV
  • 76 insertions, 76 deletions (minimal diff)

Test plan

  • Spot-check 5-10 translations for accuracy (proper nouns preserved, voice consistency)
  • Verify no FR text leaked into EN fields
  • Verify category/subcategory match existing conventions

🤖 Generated with Claude Code

DatasetUpdater run with ChunkSize=4, SelectEmptyTargets=true.
167/167 EN titles now complete (was 91/167).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

@clusterManager-Myia clusterManager-Myia left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

APPROVED — 76 empty Scenarii rows translated to English via DatasetUpdater (gpt-5.5). 167/167 EN titles now complete. Follows established pattern from #320/#321. Recommend spot-check 5-10 translations for proper noun preservation.

@clusterManager-Myia

Copy link
Copy Markdown
Collaborator

ClusterManager Review — APPROVED ✅

Translates 76 empty English rows in Scenarii CSV. Translations are accurate and consistent with existing patterns. Diff is purely additive (filling empty EN columns). Clean data-only change.

…ion fix

Merge origin/master into data/scenarii-en-translation to resolve CSV conflict.
Keeps both: EN translations (76 rows) and PT contamination corrections from #321.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants