Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048303631> ?p ?o ?g. }
- W3048303631 endingPage "103529" @default.
- W3048303631 startingPage "103529" @default.
- W3048303631 abstract "Artificial intelligence in healthcare increasingly relies on relations in knowledge graphs for algorithm development. However, many important relations are not well covered in existing knowledge graphs. We aim to develop a novel long-distance relation extraction algorithm that leverages the article section structure and is trained with bootstrapped noisy data to identify important relations for diagnosis, including may cause, may be caused by, and differential diagnosis. Known relations were extracted from semistructured web pages and a relational database and were paired with sentences containing corresponding medical concepts to form training data. The sentence form was extended to allow one concept to be in the title. An attention mechanism was applied to reduce the effect of noisily labeled sentences. Section structure embedding was added to provide additional context for relation expressions. Graph information was further incorporated into the model to differentiate the target relations whose expressions were often similar and interwoven. The extended sentence form allowed 1.75 times as many relations and 2.17 times as many sentences to be found compared to the conventional form. The various components of the proposed model all added to the accuracy. Overall, the positive sample accuracy of the proposed model was 9 percentage points higher than baseline deep learning models and 13 percentage points higher than naïve Bayes and support vector machines. Our bootstrap data preparation method and the extended sentence form could form a large training dataset to enable algorithm development and data mining efforts. Section structure embedding and graph information significantly increased prediction accuracy." @default.
- W3048303631 created "2020-08-13" @default.
- W3048303631 creator A5016359358 @default.
- W3048303631 creator A5032073558 @default.
- W3048303631 creator A5034345699 @default.
- W3048303631 creator A5037957119 @default.
- W3048303631 creator A5040501126 @default.
- W3048303631 creator A5042792242 @default.
- W3048303631 creator A5044749547 @default.
- W3048303631 creator A5056808064 @default.
- W3048303631 creator A5064842058 @default.
- W3048303631 creator A5066874145 @default.
- W3048303631 date "2020-09-01" @default.
- W3048303631 modified "2023-09-27" @default.
- W3048303631 title "Long-distance disorder-disorder relation extraction with bootstrapped noisy data" @default.
- W3048303631 cites W2052222137 @default.
- W3048303631 cites W2076042203 @default.
- W3048303631 cites W2081580037 @default.
- W3048303631 cites W2094728533 @default.
- W3048303631 cites W2107598941 @default.
- W3048303631 cites W2120814856 @default.
- W3048303631 cites W2136410628 @default.
- W3048303631 cites W2138627627 @default.
- W3048303631 cites W2250539671 @default.
- W3048303631 cites W2339530503 @default.
- W3048303631 cites W2470673105 @default.
- W3048303631 cites W2511964075 @default.
- W3048303631 cites W2515462165 @default.
- W3048303631 cites W2604748391 @default.
- W3048303631 cites W2964167098 @default.
- W3048303631 cites W3004844052 @default.
- W3048303631 doi "https://doi.org/10.1016/j.jbi.2020.103529" @default.
- W3048303631 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32771539" @default.
- W3048303631 hasPublicationYear "2020" @default.
- W3048303631 type Work @default.
- W3048303631 sameAs 3048303631 @default.
- W3048303631 citedByCount "3" @default.
- W3048303631 countsByYear W30483036312020 @default.
- W3048303631 countsByYear W30483036312022 @default.
- W3048303631 countsByYear W30483036312023 @default.
- W3048303631 crossrefType "journal-article" @default.
- W3048303631 hasAuthorship W3048303631A5016359358 @default.
- W3048303631 hasAuthorship W3048303631A5032073558 @default.
- W3048303631 hasAuthorship W3048303631A5034345699 @default.
- W3048303631 hasAuthorship W3048303631A5037957119 @default.
- W3048303631 hasAuthorship W3048303631A5040501126 @default.
- W3048303631 hasAuthorship W3048303631A5042792242 @default.
- W3048303631 hasAuthorship W3048303631A5044749547 @default.
- W3048303631 hasAuthorship W3048303631A5056808064 @default.
- W3048303631 hasAuthorship W3048303631A5064842058 @default.
- W3048303631 hasAuthorship W3048303631A5066874145 @default.
- W3048303631 hasConcept C119857082 @default.
- W3048303631 hasConcept C12267149 @default.
- W3048303631 hasConcept C124101348 @default.
- W3048303631 hasConcept C132525143 @default.
- W3048303631 hasConcept C151730666 @default.
- W3048303631 hasConcept C153604712 @default.
- W3048303631 hasConcept C154945302 @default.
- W3048303631 hasConcept C195807954 @default.
- W3048303631 hasConcept C204321447 @default.
- W3048303631 hasConcept C25343380 @default.
- W3048303631 hasConcept C2777530160 @default.
- W3048303631 hasConcept C2779343474 @default.
- W3048303631 hasConcept C41008148 @default.
- W3048303631 hasConcept C41608201 @default.
- W3048303631 hasConcept C52001869 @default.
- W3048303631 hasConcept C80444323 @default.
- W3048303631 hasConcept C86803240 @default.
- W3048303631 hasConceptScore W3048303631C119857082 @default.
- W3048303631 hasConceptScore W3048303631C12267149 @default.
- W3048303631 hasConceptScore W3048303631C124101348 @default.
- W3048303631 hasConceptScore W3048303631C132525143 @default.
- W3048303631 hasConceptScore W3048303631C151730666 @default.
- W3048303631 hasConceptScore W3048303631C153604712 @default.
- W3048303631 hasConceptScore W3048303631C154945302 @default.
- W3048303631 hasConceptScore W3048303631C195807954 @default.
- W3048303631 hasConceptScore W3048303631C204321447 @default.
- W3048303631 hasConceptScore W3048303631C25343380 @default.
- W3048303631 hasConceptScore W3048303631C2777530160 @default.
- W3048303631 hasConceptScore W3048303631C2779343474 @default.
- W3048303631 hasConceptScore W3048303631C41008148 @default.
- W3048303631 hasConceptScore W3048303631C41608201 @default.
- W3048303631 hasConceptScore W3048303631C52001869 @default.
- W3048303631 hasConceptScore W3048303631C80444323 @default.
- W3048303631 hasConceptScore W3048303631C86803240 @default.
- W3048303631 hasFunder F4320321001 @default.
- W3048303631 hasFunder F4320322392 @default.
- W3048303631 hasFunder F4320322919 @default.
- W3048303631 hasFunder F4320335777 @default.
- W3048303631 hasLocation W30483036311 @default.
- W3048303631 hasOpenAccess W3048303631 @default.
- W3048303631 hasPrimaryLocation W30483036311 @default.
- W3048303631 hasRelatedWork W2368651715 @default.
- W3048303631 hasRelatedWork W2539163683 @default.
- W3048303631 hasRelatedWork W2595988085 @default.
- W3048303631 hasRelatedWork W2609844752 @default.
- W3048303631 hasRelatedWork W2979979539 @default.
- W3048303631 hasRelatedWork W3101091249 @default.