HERIT adapts translation models for Hanja-to-English historical archives
Authors use RAG on Hanja-Korean corpora to build pseudo-labels, cut temporal bias, and report gains over baselines.
Stories per day · 30 days
Relateddomain-adaptation1grpo1hanja1historical-archives1machine-translation1rag1reinforcement-learning1speech-recognition1whisper1
2 stories, newest first · one card per story
Stories tagged #pseudo-labeling
GRPO treats ASR pseudo-labels as rewards rather than targets
In banking audio, GRPO cut WER 29.3% to 56.2% relative to SFT and copied 27% of teacher errors.