A fusion of encoder ensemble scores and LLM re-ranking improves automated relevance scoring for semantic search test collections in low-resource German, but the fusion thresholds are tuned on the test data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
A fusion of encoder ensemble scores and LLM re-ranking improves automated relevance scoring for semantic search test collections in low-resource German, but the fusion thresholds are tuned on the test data.