Hyperbolic embeddings derived from language models retrieve the most specific subsuming concepts in SNOMED CT for out-of-vocabulary queries and outperform SBERT, SapBERT, and lexical baselines on three constructed datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Retrieval with Out-Of-Vocabulary Queries: A Case Study on SNOMED CT
Hyperbolic embeddings derived from language models retrieve the most specific subsuming concepts in SNOMED CT for out-of-vocabulary queries and outperform SBERT, SapBERT, and lexical baselines on three constructed datasets.