Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092008332> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3092008332 endingPage "1546" @default.
- W3092008332 startingPage "1538" @default.
- W3092008332 abstract "Abstract Objective The study sought to explore the use of deep learning techniques to measure the semantic relatedness between Unified Medical Language System (UMLS) concepts. Materials and Methods Concept sentence embeddings were generated for UMLS concepts by applying the word embedding models BioWordVec and various flavors of BERT to concept sentences formed by concatenating UMLS terms. Graph embeddings were generated by the graph convolutional networks and 4 knowledge graph embedding models, using graphs built from UMLS hierarchical relations. Semantic relatedness was measured by the cosine between the concepts’ embedding vectors. Performance was compared with 2 traditional path-based (shortest path and Leacock-Chodorow) measurements and the publicly available concept embeddings, cui2vec, generated from large biomedical corpora. The concept sentence embeddings were also evaluated on a word sense disambiguation (WSD) task. Reference standards used included the semantic relatedness and semantic similarity datasets from the University of Minnesota, concept pairs generated from the Standardized MedDRA Queries and the MeSH (Medical Subject Headings) WSD corpus. Results Sentence embeddings generated by BioWordVec outperformed all other methods used individually in semantic relatedness measurements. Graph convolutional network graph embedding uniformly outperformed path-based measurements and was better than some word embeddings for the Standardized MedDRA Queries dataset. When used together, combined word and graph embedding achieved the best performance in all datasets. For WSD, the enhanced versions of BERT outperformed BioWordVec. Conclusions Word and graph embedding techniques can be used to harness terms and relations in the UMLS to measure semantic relatedness between concepts. Concept sentence embedding outperforms path-based measurements and cui2vec, and can be further enhanced by combining with graph embedding." @default.
- W3092008332 created "2020-10-15" @default.
- W3092008332 creator A5031594710 @default.
- W3092008332 creator A5089104211 @default.
- W3092008332 date "2020-10-01" @default.
- W3092008332 modified "2023-10-05" @default.
- W3092008332 title "Use of word and graph embedding to measure semantic relatedness between Unified Medical Language System concepts" @default.
- W3092008332 cites W2028102159 @default.
- W3092008332 cites W2041025542 @default.
- W3092008332 cites W2084377579 @default.
- W3092008332 cites W2136930489 @default.
- W3092008332 cites W2149600008 @default.
- W3092008332 cites W2159583324 @default.
- W3092008332 cites W2215513433 @default.
- W3092008332 cites W2493916176 @default.
- W3092008332 cites W2509406088 @default.
- W3092008332 cites W2617156436 @default.
- W3092008332 cites W2911489562 @default.
- W3092008332 cites W2941748305 @default.
- W3092008332 cites W2944400536 @default.
- W3092008332 cites W2963224980 @default.
- W3092008332 cites W2963923670 @default.
- W3092008332 doi "https://doi.org/10.1093/jamia/ocaa136" @default.
- W3092008332 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7566472" @default.
- W3092008332 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33029614" @default.
- W3092008332 hasPublicationYear "2020" @default.
- W3092008332 type Work @default.
- W3092008332 sameAs 3092008332 @default.
- W3092008332 citedByCount "19" @default.
- W3092008332 countsByYear W30920083322020 @default.
- W3092008332 countsByYear W30920083322021 @default.
- W3092008332 countsByYear W30920083322022 @default.
- W3092008332 countsByYear W30920083322023 @default.
- W3092008332 crossrefType "journal-article" @default.
- W3092008332 hasAuthorship W3092008332A5031594710 @default.
- W3092008332 hasAuthorship W3092008332A5089104211 @default.
- W3092008332 hasBestOaLocation W30920083321 @default.
- W3092008332 hasConcept C130318100 @default.
- W3092008332 hasConcept C132525143 @default.
- W3092008332 hasConcept C154945302 @default.
- W3092008332 hasConcept C204321447 @default.
- W3092008332 hasConcept C23123220 @default.
- W3092008332 hasConcept C2777462759 @default.
- W3092008332 hasConcept C2777530160 @default.
- W3092008332 hasConcept C41008148 @default.
- W3092008332 hasConcept C41608201 @default.
- W3092008332 hasConcept C69505689 @default.
- W3092008332 hasConcept C80444323 @default.
- W3092008332 hasConceptScore W3092008332C130318100 @default.
- W3092008332 hasConceptScore W3092008332C132525143 @default.
- W3092008332 hasConceptScore W3092008332C154945302 @default.
- W3092008332 hasConceptScore W3092008332C204321447 @default.
- W3092008332 hasConceptScore W3092008332C23123220 @default.
- W3092008332 hasConceptScore W3092008332C2777462759 @default.
- W3092008332 hasConceptScore W3092008332C2777530160 @default.
- W3092008332 hasConceptScore W3092008332C41008148 @default.
- W3092008332 hasConceptScore W3092008332C41608201 @default.
- W3092008332 hasConceptScore W3092008332C69505689 @default.
- W3092008332 hasConceptScore W3092008332C80444323 @default.
- W3092008332 hasIssue "10" @default.
- W3092008332 hasLocation W30920083321 @default.
- W3092008332 hasLocation W30920083322 @default.
- W3092008332 hasOpenAccess W3092008332 @default.
- W3092008332 hasPrimaryLocation W30920083321 @default.
- W3092008332 hasRelatedWork W2804271283 @default.
- W3092008332 hasRelatedWork W2990896562 @default.
- W3092008332 hasRelatedWork W3006690199 @default.
- W3092008332 hasRelatedWork W3161027543 @default.
- W3092008332 hasRelatedWork W3212418102 @default.
- W3092008332 hasRelatedWork W4221152557 @default.
- W3092008332 hasRelatedWork W4285309062 @default.
- W3092008332 hasRelatedWork W4288026180 @default.
- W3092008332 hasRelatedWork W4299611961 @default.
- W3092008332 hasRelatedWork W4312046383 @default.
- W3092008332 hasVolume "27" @default.
- W3092008332 isParatext "false" @default.
- W3092008332 isRetracted "false" @default.
- W3092008332 magId "3092008332" @default.
- W3092008332 workType "article" @default.