ELERAG integrates Wikidata entity linking with hybrid RRF re-ranking into RAG and outperforms baselines on a custom Italian academic dataset while cross-encoder methods win on the general SQuAD-it dataset.
Research on the Development of College Japanese Courses Oriented towards 'Engineering + Japanese'
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A RAG+prompt system improves BLEU scores for Japanese-Chinese NMCC translations from 24.28 to 29.96 as the knowledge base grows from 0 to 2,000 examples.
citing papers explorer
-
Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms
ELERAG integrates Wikidata entity linking with hybrid RRF re-ranking into RAG and outperforms baselines on a custom Italian academic dataset while cross-encoder methods win on the general SQuAD-it dataset.
-
From prompting to evidence-based translation: A RAG+prompt system for Japanese-Chinese translation and its pedagogical potential
A RAG+prompt system improves BLEU scores for Japanese-Chinese NMCC translations from 24.28 to 29.96 as the knowledge base grows from 0 to 2,000 examples.