2026-10-11T17:56:45Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33944665 2026-09-20T08:01:03Z category_28822 category_29530 item_type_3 month_year_09_2026

<b>Bee-RAG for Auditable Japanese-Mandarin Chinese Sentence Alignment with Retrieval Evidence and Multi-objective Calibration</b> Xiaoying Pan (7016603) Applied computing not elsewhere classified Other language, communication and culture not elsewhere classified Japanese-Mandarin Chinese corpus retrieval evidence artificial bee colony <p dir="ltr">Japanese–Mandarin Chinese translation-memory alignment requires accurate cross-lingual candidate ranking, efficient adaptation under limited bilingual supervision, and reliable evidence support for practical corpus curation. Existing approaches often rely primarily on direct semantic similarity or batch-level neighborhood correction, making it difficult to jointly exploit lightweight task adaptation, bilingual retrieval evidence, selective review, and provenance-preserving output within a unified CPU-efficient pipeline. This study proposes an auditable sentence-alignment framework that integrates a frozen multilingual MiniLM encoder, projection-level contrastive adaptation, retrieval-derived bilingual evidence, and multiobjective bee-colony calibration.</p> 2026-09-20T08:01:03Z Dataset Dataset 10.6084/m9.figshare.33944665.v1 https://figshare.com/articles/dataset/_b_Bee-RAG_for_Auditable_Japanese-Mandarin_Chinese_Sentence_Alignment_with_Retrieval_Evidence_and_Multi-objective_Calibration_b_/33944665 CC BY 4.0