Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887388812> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2887388812 endingPage "551" @default.
- W2887388812 startingPage "543" @default.
- W2887388812 abstract "Term weighting is an essential step to process textual data and generate input data (vector) for machine learning algorithms. In order to appropriately represent documents into computable forms for a certain task (such as text classification, clustering, sentiment analysis, recommendation and information retrieval), semantic term weighting which considers term meanings is significant for specific applications of machine learning. Two challenging issues of semantic term weighting for clinical texts are how to determine the meaning of a medical term in a given clinical text and how to give semantic weights for a huge amount of distinct terms in clinical texts. To address those challenges, this work proposes a two-phase framework for determining semantic weights of terms in clinical texts. The proposed framework derives a two-part hierarchy where each of the nodes is categories of terms. All terms in a clinical text is classified into the categories in the hierarchy and terms in the leaf nodes are assigned with the same semantic weights. Fundamentally, the deeper the hierarchy, the higher the semantic weights. The first phase classifies all terms into the categories which are commonly significant for any tasks, by using UMLS and ICD-10. These categories are organized at the first part of the hierarchy. The second phase flexibly organizes specific categories for a certain task as the second part of the hierarchy as well as the subcategories of the first part, by specific medical domain knowledge regarding the aspect under consideration. The implementation of the proposed framework for mortality prediction with semantic weights is validated by experimental comparative evaluation using the well-known EMRs database MIMIC II. The experimental results showed that the performance is considerably improved when combining frequency-based weights and semantic weights with its significant difference derived from a paired t-test. Although the proposed framework can be applied to only medical domain, various tasks in medical domain can be covered by the proposed framework which flexibly organizes the second part (deeper levels in the hierarchy) by specific medical knowledge regarding the aspect under consideration." @default.
- W2887388812 created "2018-08-22" @default.
- W2887388812 creator A5036418930 @default.
- W2887388812 creator A5047113743 @default.
- W2887388812 date "2018-12-01" @default.
- W2887388812 modified "2023-09-23" @default.
- W2887388812 title "Semantic term weighting for clinical texts" @default.
- W2887388812 cites W1775813496 @default.
- W2887388812 cites W1977823755 @default.
- W2887388812 cites W1978394996 @default.
- W2887388812 cites W1998560003 @default.
- W2887388812 cites W2014002054 @default.
- W2887388812 cites W2046788142 @default.
- W2887388812 cites W2115985394 @default.
- W2887388812 cites W2124119950 @default.
- W2887388812 cites W2125207043 @default.
- W2887388812 cites W2125935535 @default.
- W2887388812 cites W2131273899 @default.
- W2887388812 cites W2131660156 @default.
- W2887388812 cites W2137079713 @default.
- W2887388812 cites W2159583324 @default.
- W2887388812 cites W2326291605 @default.
- W2887388812 cites W2410109979 @default.
- W2887388812 cites W2467651252 @default.
- W2887388812 doi "https://doi.org/10.1016/j.eswa.2018.08.028" @default.
- W2887388812 hasPublicationYear "2018" @default.
- W2887388812 type Work @default.
- W2887388812 sameAs 2887388812 @default.
- W2887388812 citedByCount "5" @default.
- W2887388812 countsByYear W28873888122019 @default.
- W2887388812 countsByYear W28873888122020 @default.
- W2887388812 countsByYear W28873888122021 @default.
- W2887388812 countsByYear W28873888122023 @default.
- W2887388812 crossrefType "journal-article" @default.
- W2887388812 hasAuthorship W2887388812A5036418930 @default.
- W2887388812 hasAuthorship W2887388812A5047113743 @default.
- W2887388812 hasConcept C121332964 @default.
- W2887388812 hasConcept C126838900 @default.
- W2887388812 hasConcept C130318100 @default.
- W2887388812 hasConcept C154945302 @default.
- W2887388812 hasConcept C162324750 @default.
- W2887388812 hasConcept C183115368 @default.
- W2887388812 hasConcept C187736073 @default.
- W2887388812 hasConcept C204321447 @default.
- W2887388812 hasConcept C2129575 @default.
- W2887388812 hasConcept C23123220 @default.
- W2887388812 hasConcept C2777946921 @default.
- W2887388812 hasConcept C2780451532 @default.
- W2887388812 hasConcept C31170391 @default.
- W2887388812 hasConcept C34447519 @default.
- W2887388812 hasConcept C41008148 @default.
- W2887388812 hasConcept C511149849 @default.
- W2887388812 hasConcept C61797465 @default.
- W2887388812 hasConcept C62520636 @default.
- W2887388812 hasConcept C69505689 @default.
- W2887388812 hasConcept C71924100 @default.
- W2887388812 hasConceptScore W2887388812C121332964 @default.
- W2887388812 hasConceptScore W2887388812C126838900 @default.
- W2887388812 hasConceptScore W2887388812C130318100 @default.
- W2887388812 hasConceptScore W2887388812C154945302 @default.
- W2887388812 hasConceptScore W2887388812C162324750 @default.
- W2887388812 hasConceptScore W2887388812C183115368 @default.
- W2887388812 hasConceptScore W2887388812C187736073 @default.
- W2887388812 hasConceptScore W2887388812C204321447 @default.
- W2887388812 hasConceptScore W2887388812C2129575 @default.
- W2887388812 hasConceptScore W2887388812C23123220 @default.
- W2887388812 hasConceptScore W2887388812C2777946921 @default.
- W2887388812 hasConceptScore W2887388812C2780451532 @default.
- W2887388812 hasConceptScore W2887388812C31170391 @default.
- W2887388812 hasConceptScore W2887388812C34447519 @default.
- W2887388812 hasConceptScore W2887388812C41008148 @default.
- W2887388812 hasConceptScore W2887388812C511149849 @default.
- W2887388812 hasConceptScore W2887388812C61797465 @default.
- W2887388812 hasConceptScore W2887388812C62520636 @default.
- W2887388812 hasConceptScore W2887388812C69505689 @default.
- W2887388812 hasConceptScore W2887388812C71924100 @default.
- W2887388812 hasLocation W28873888121 @default.
- W2887388812 hasOpenAccess W2887388812 @default.
- W2887388812 hasPrimaryLocation W28873888121 @default.
- W2887388812 hasRelatedWork W1894023216 @default.
- W2887388812 hasRelatedWork W2031477912 @default.
- W2887388812 hasRelatedWork W2033338885 @default.
- W2887388812 hasRelatedWork W2353314619 @default.
- W2887388812 hasRelatedWork W2376633828 @default.
- W2887388812 hasRelatedWork W2380556669 @default.
- W2887388812 hasRelatedWork W2887388812 @default.
- W2887388812 hasRelatedWork W2977842567 @default.
- W2887388812 hasRelatedWork W4225081787 @default.
- W2887388812 hasRelatedWork W4243530889 @default.
- W2887388812 hasVolume "114" @default.
- W2887388812 isParatext "false" @default.
- W2887388812 isRetracted "false" @default.
- W2887388812 magId "2887388812" @default.
- W2887388812 workType "article" @default.