This paper measures the end-to-end impact of inserting a Jejueo→Standard-Korean normalization layer before a retrieval-augmented generation (RAG) QA system and of merging results from two retrieval paths. Under an identical stack, we compare: (i) the original-Jejueo retrieval path, retrieve with the unnormalized query (RAW), (ii) the normalized-to-Standard-Korean retrieval path, retrieve with the query rewritten by our Jejueo→Standard-Korean normalizer (NORM), and (iii) the merged path, deduplicate and re-rank the union of RAW and NORM candidates (DUAL). Using the Jejueo Interview Transcripts, lightweight preprocessing, and a compact LoRA-based normalizer, we evaluate retrieval/ranking (Hit@5, MRR@5), evidence attribution (Attrib-F1), answer quality (Token-F1/ROUGE-L), diversity (ILD@5), and hallucination. Normalization alone improves top-rank concentration and citation precision over RAW (Token-F1 +6–7; Attrib-F1 +0.09; Hit@5 ≈ +0.11), and DUAL adds further gains (≈ +4 Token-F1; +0.06 Attrib-F1), increases diversity, and lowers hallucination (≈ −1.7%p). Error analyses trace benefits to aligning Jejueo sentence-final endings, discourse markers, and idioms that otherwise destabilize retrieval; DUAL also hedges over/under-substitution from imperfect normalization. Our intent is practical: use DUAL by default for robustness, and prefer NORM alone when normalization confidence is high and latency/compute budgets are tight.
목차
Abstract 1. Introduction 2. Related Work 2.1 Jejueo Normalization and Translation 2.2 Retrieval-Augmented Generation (RAG) 2.3 Dialectal Question Answering (QA) 3. Method 3.1 Data 3.2 Normalization 3.3 Dual-Path RAG 3.4 Training Procedure 4. Results 5. Discussion 6. Conclusion References
키워드
Jejueo NormalizationRetrieval-Augmented Generation (RAG)Dual Retrieval PathDialectal Question AnsweringLarge Language Model (LLM)Low-Resource NLPKorean Dialect Processing
저자
Gwangmi Cho [ Doctoral Course, Department of Immersive Convergence Content, Kwangwoon University, Korea ]
Jongbeom Ku [ Doctoral Course, Department of Immersive Convergence Content, Kwangwoon University, Korea ]
Hobyung Chae [ Professor, Industry-Academic Cooperation Foundation, Kwangwoon University, Korea ]
Corresponding Author