FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3143149837> ?p ?o ?g. }

• W3143149837 endingPage "12549" @default.
• W3143149837 startingPage "12535" @default.
• W3143149837 abstract "Electronic health records (EHRs) in hospital information systems contain patients’ diagnoses and treatments, so EHRs are essential to clinical data mining. Of all the tasks in the mining process, Chinese word segmentation (CWS) is a fundamental and important one, and most state-of-the-art methods greatly rely on large scale of manually annotated data. Since annotation is time-consuming and expensive, efforts have been devoted to techniques, such as active learning, to locate the most informative samples for modeling. In this paper, we follow the trend and present an active learning method for CWS in EHRs. Specifically, a new sampling strategy combining normalized entropy with loss prediction (NE–LP) is proposed to select the most valuable data. Meanwhile, to minimize the computational cost of learning, we propose a joint model including a word segmenter and a loss prediction model. Furthermore, to capture interactions between adjacent characters, bigram features are also applied in the joint model. To illustrate the effectiveness of NE–LP, we conducted experiments on EHRs collected from the Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine. The results demonstrate that NE–LP consistently outperforms conventional uncertainty-based sampling strategies for active learning in CWS" @default.
• W3143149837 created "2021-04-13" @default.
• W3143149837 creator A5011711527 @default.
• W3143149837 creator A5021549473 @default.
• W3143149837 creator A5071839367 @default.
• W3143149837 creator A5074965982 @default.
• W3143149837 date "2021-03-29" @default.
• W3143149837 modified "2023-09-25" @default.
• W3143149837 title "NE–LP: Normalized entropy- and loss prediction-based sampling for active learning in Chinese word segmentation on EHRs" @default.
• W3143149837 cites W1979145089 @default.
• W3143149837 cites W2036516910 @default.
• W3143149837 cites W2128518360 @default.
• W3143149837 cites W2151831732 @default.
• W3143149837 cites W2159583324 @default.
• W3143149837 cites W2233838193 @default.
• W3143149837 cites W2250739653 @default.
• W3143149837 cites W2252069213 @default.
• W3143149837 cites W2779904079 @default.
• W3143149837 cites W2782397925 @default.
• W3143149837 cites W2893384461 @default.
• W3143149837 cites W2910398204 @default.
• W3143149837 cites W2911855264 @default.
• W3143149837 cites W2951911250 @default.
• W3143149837 cites W2955738169 @default.
• W3143149837 cites W2956371155 @default.
• W3143149837 cites W2962885853 @default.
• W3143149837 cites W2963571188 @default.
• W3143149837 cites W3035030897 @default.
• W3143149837 cites W3041526152 @default.
• W3143149837 cites W3081260973 @default.
• W3143149837 cites W3083429640 @default.
• W3143149837 cites W3087375354 @default.
• W3143149837 cites W3087495852 @default.
• W3143149837 cites W3088324128 @default.
• W3143149837 cites W3104309049 @default.
• W3143149837 cites W3105966348 @default.
• W3143149837 cites W3129023631 @default.
• W3143149837 cites W3153512306 @default.
• W3143149837 doi "https://doi.org/10.1007/s00521-021-05896-w" @default.
• W3143149837 hasPublicationYear "2021" @default.
• W3143149837 type Work @default.
• W3143149837 sameAs 3143149837 @default.
• W3143149837 citedByCount "7" @default.
• W3143149837 countsByYear W31431498372021 @default.
• W3143149837 countsByYear W31431498372022 @default.
• W3143149837 countsByYear W31431498372023 @default.
• W3143149837 crossrefType "journal-article" @default.
• W3143149837 hasAuthorship W3143149837A5011711527 @default.
• W3143149837 hasAuthorship W3143149837A5021549473 @default.
• W3143149837 hasAuthorship W3143149837A5071839367 @default.
• W3143149837 hasAuthorship W3143149837A5074965982 @default.
• W3143149837 hasBestOaLocation W31431498372 @default.
• W3143149837 hasConcept C106131492 @default.
• W3143149837 hasConcept C106301342 @default.
• W3143149837 hasConcept C108757681 @default.
• W3143149837 hasConcept C119857082 @default.
• W3143149837 hasConcept C121332964 @default.
• W3143149837 hasConcept C124101348 @default.
• W3143149837 hasConcept C137546455 @default.
• W3143149837 hasConcept C140779682 @default.
• W3143149837 hasConcept C153180895 @default.
• W3143149837 hasConcept C154945302 @default.
• W3143149837 hasConcept C160735492 @default.
• W3143149837 hasConcept C162324750 @default.
• W3143149837 hasConcept C167981619 @default.
• W3143149837 hasConcept C204321447 @default.
• W3143149837 hasConcept C2524010 @default.
• W3143149837 hasConcept C2776321320 @default.
• W3143149837 hasConcept C3019952477 @default.
• W3143149837 hasConcept C31972630 @default.
• W3143149837 hasConcept C33923547 @default.
• W3143149837 hasConcept C41008148 @default.
• W3143149837 hasConcept C50522688 @default.
• W3143149837 hasConcept C62520636 @default.
• W3143149837 hasConcept C89600930 @default.
• W3143149837 hasConcept C90805587 @default.
• W3143149837 hasConcept C9679016 @default.
• W3143149837 hasConcept C98501671 @default.
• W3143149837 hasConceptScore W3143149837C106131492 @default.
• W3143149837 hasConceptScore W3143149837C106301342 @default.
• W3143149837 hasConceptScore W3143149837C108757681 @default.
• W3143149837 hasConceptScore W3143149837C119857082 @default.
• W3143149837 hasConceptScore W3143149837C121332964 @default.
• W3143149837 hasConceptScore W3143149837C124101348 @default.
• W3143149837 hasConceptScore W3143149837C137546455 @default.
• W3143149837 hasConceptScore W3143149837C140779682 @default.
• W3143149837 hasConceptScore W3143149837C153180895 @default.
• W3143149837 hasConceptScore W3143149837C154945302 @default.
• W3143149837 hasConceptScore W3143149837C160735492 @default.
• W3143149837 hasConceptScore W3143149837C162324750 @default.
• W3143149837 hasConceptScore W3143149837C167981619 @default.
• W3143149837 hasConceptScore W3143149837C204321447 @default.
• W3143149837 hasConceptScore W3143149837C2524010 @default.
• W3143149837 hasConceptScore W3143149837C2776321320 @default.
• W3143149837 hasConceptScore W3143149837C3019952477 @default.
• W3143149837 hasConceptScore W3143149837C31972630 @default.
• W3143149837 hasConceptScore W3143149837C33923547 @default.
• W3143149837 hasConceptScore W3143149837C41008148 @default.

• next