An LLM-generated candidate list, averaged in embedding space and ranked against dictionary terms, outperforms several supervised reverse dictionary models on generalization splits.
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
-
GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary
An LLM-generated candidate list, averaged in embedding space and ranked against dictionary terms, outperforms several supervised reverse dictionary models on generalization splits.