v0.1.7: rescore NLLB + opus-mt against certified-translator FLORES refs#22
Merged
Conversation
NLLB and opus-mt re-run for all 8 extension pairs (en-ru N=10, others N=13 each). Identity and DeepL re-scored. Leaderboard rebuilt. Key results (chrF, oracle-layout): DeepL 78.20 [75.2, 81.7] 6/16 pairs (unchanged, 5 docs per pair) NLLB 73.71 [72.5, 74.9] 16/16 pairs (was 74.02 at v0.1.6) opus-mt 68.60 [67.1, 70.0] 16/16 pairs (was 69.16 at v0.1.6) Notable per-pair findings: en-uz chrF≈0 for both NLLB and opus-mt (Uzbek-Latin near-fail); en-ko chrF 2.58 for opus-mt vs 36.88 for NLLB. COMET-Kiwi leaderboard marked stale pending re-score. Fix skip_no_ref bug in run_nllb (parameter was declared but not used in loop logic).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
skip_no_ref); results now scored against v0.1.7 certified-translator FLORES refsskip_no_refbug inrun_nllb: parameter was declared but not applied in the loop bodyLEADERBOARD.mdandleaderboard/index.htmlwith v0.1.7 scores; COMET-Kiwi section marked stale pending re-runScores (chrF, oracle-layout, v0.1.7)
Per-pair highlights
Test plan
pytest tests/test_v016.py::test_real_v016_manifest_per_pair_counts— extension pair counts ≥10/13🤖 Generated with Claude Code