Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381309010> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4381309010 endingPage "779" @default.
- W4381309010 startingPage "765" @default.
- W4381309010 abstract "Machine learning (ML) systems are widely used for automatic entity recognition in pharmacovigilance. Publicly available datasets do not allow the use of annotated entities independently, focusing on small entity subsets or on single language registers (informal or scientific language). The objective of the current study was to create a dataset that enables independent usage of entities, explores the performance of predictive ML models on different registers, and introduces a method to investigate entity cut-off performance.A dataset has been created combining different registers with 18 different entities. We applied this dataset to compare the performance of integrated models with models created with single language registers only. We introduced fractional stratified k-fold cross-validation to determine model performance on entity level by using training dataset fractions. We investigated the course of entity performance with fractions of training datasets and evaluated entity peak and cut-off performance.The dataset combines 1400 records (scientific language: 790; informal language: 610) with 2622 sentences and 9989 entity occurrences and combines data from external (801 records) and internal sources (599 records). We demonstrated that single language register models underperform compared to integrated models trained with multiple language registers.A manually annotated dataset with a variety of different pharmaceutical and biomedical entities was created and is made available to the research community. Our results show that models that combine different registers provide better maintainability, have higher robustness, and have similar or higher performance. Fractional stratified k-fold cross-validation allows the evaluation of training data sufficiency on the entity level." @default.
- W4381309010 created "2023-06-21" @default.
- W4381309010 creator A5014595566 @default.
- W4381309010 creator A5018456037 @default.
- W4381309010 date "2023-06-20" @default.
- W4381309010 modified "2023-10-14" @default.
- W4381309010 title "Provision and Characterization of a Corpus for Pharmaceutical, Biomedical Named Entity Recognition for Pharmacovigilance: Evaluation of Language Registers and Training Data Sufficiency" @default.
- W4381309010 cites W2129767020 @default.
- W4381309010 cites W2131546905 @default.
- W4381309010 cites W2161182098 @default.
- W4381309010 cites W2487770199 @default.
- W4381309010 cites W2895296143 @default.
- W4381309010 cites W2911489562 @default.
- W4381309010 cites W2963716420 @default.
- W4381309010 cites W2972736338 @default.
- W4381309010 cites W2979250794 @default.
- W4381309010 cites W2996894939 @default.
- W4381309010 cites W3004025777 @default.
- W4381309010 cites W3126506274 @default.
- W4381309010 cites W3169283738 @default.
- W4381309010 cites W3169483174 @default.
- W4381309010 cites W3199307809 @default.
- W4381309010 cites W3213241618 @default.
- W4381309010 cites W4280534881 @default.
- W4381309010 cites W4319062633 @default.
- W4381309010 doi "https://doi.org/10.1007/s40264-023-01322-3" @default.
- W4381309010 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37338799" @default.
- W4381309010 hasPublicationYear "2023" @default.
- W4381309010 type Work @default.
- W4381309010 citedByCount "0" @default.
- W4381309010 crossrefType "journal-article" @default.
- W4381309010 hasAuthorship W4381309010A5014595566 @default.
- W4381309010 hasAuthorship W4381309010A5018456037 @default.
- W4381309010 hasBestOaLocation W43813090101 @default.
- W4381309010 hasConcept C104317684 @default.
- W4381309010 hasConcept C115903868 @default.
- W4381309010 hasConcept C119857082 @default.
- W4381309010 hasConcept C124101348 @default.
- W4381309010 hasConcept C126322002 @default.
- W4381309010 hasConcept C137293760 @default.
- W4381309010 hasConcept C154945302 @default.
- W4381309010 hasConcept C160713754 @default.
- W4381309010 hasConcept C162324750 @default.
- W4381309010 hasConcept C185592680 @default.
- W4381309010 hasConcept C187736073 @default.
- W4381309010 hasConcept C197934379 @default.
- W4381309010 hasConcept C204321447 @default.
- W4381309010 hasConcept C2779135771 @default.
- W4381309010 hasConcept C2780451532 @default.
- W4381309010 hasConcept C41008148 @default.
- W4381309010 hasConcept C55493867 @default.
- W4381309010 hasConcept C57658597 @default.
- W4381309010 hasConcept C63479239 @default.
- W4381309010 hasConcept C71924100 @default.
- W4381309010 hasConcept C77088390 @default.
- W4381309010 hasConceptScore W4381309010C104317684 @default.
- W4381309010 hasConceptScore W4381309010C115903868 @default.
- W4381309010 hasConceptScore W4381309010C119857082 @default.
- W4381309010 hasConceptScore W4381309010C124101348 @default.
- W4381309010 hasConceptScore W4381309010C126322002 @default.
- W4381309010 hasConceptScore W4381309010C137293760 @default.
- W4381309010 hasConceptScore W4381309010C154945302 @default.
- W4381309010 hasConceptScore W4381309010C160713754 @default.
- W4381309010 hasConceptScore W4381309010C162324750 @default.
- W4381309010 hasConceptScore W4381309010C185592680 @default.
- W4381309010 hasConceptScore W4381309010C187736073 @default.
- W4381309010 hasConceptScore W4381309010C197934379 @default.
- W4381309010 hasConceptScore W4381309010C204321447 @default.
- W4381309010 hasConceptScore W4381309010C2779135771 @default.
- W4381309010 hasConceptScore W4381309010C2780451532 @default.
- W4381309010 hasConceptScore W4381309010C41008148 @default.
- W4381309010 hasConceptScore W4381309010C55493867 @default.
- W4381309010 hasConceptScore W4381309010C57658597 @default.
- W4381309010 hasConceptScore W4381309010C63479239 @default.
- W4381309010 hasConceptScore W4381309010C71924100 @default.
- W4381309010 hasConceptScore W4381309010C77088390 @default.
- W4381309010 hasIssue "8" @default.
- W4381309010 hasLocation W43813090101 @default.
- W4381309010 hasLocation W43813090102 @default.
- W4381309010 hasLocation W43813090103 @default.
- W4381309010 hasOpenAccess W4381309010 @default.
- W4381309010 hasPrimaryLocation W43813090101 @default.
- W4381309010 hasRelatedWork W1978990931 @default.
- W4381309010 hasRelatedWork W2359001871 @default.
- W4381309010 hasRelatedWork W2405038964 @default.
- W4381309010 hasRelatedWork W2773616286 @default.
- W4381309010 hasRelatedWork W2947903144 @default.
- W4381309010 hasRelatedWork W3088296309 @default.
- W4381309010 hasRelatedWork W3136915866 @default.
- W4381309010 hasRelatedWork W4281971828 @default.
- W4381309010 hasRelatedWork W4297811573 @default.
- W4381309010 hasRelatedWork W4323240841 @default.
- W4381309010 hasVolume "46" @default.
- W4381309010 isParatext "false" @default.
- W4381309010 isRetracted "false" @default.
- W4381309010 workType "article" @default.