Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886342253> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2886342253 abstract "We present a machine learning pipeline that identifies key sentences in abstracts of oncological articles to aid evidence-based medicine. This problem is characterized by the lack of gold standard datasets, data imbalance and thematic differences between available silver standard corpora. Additionally, available training and target data differs with regard to their domain (professional summaries vs. sentences in abstracts). This makes supervised machine learning inapplicable. We propose the use of two semi-supervised machine learning approaches: To mitigate difficulties arising from heterogeneous data sources, overcome data imbalance and create reliable training data we propose using transductive learning from positive and unlabelled data (PU Learning). For obtaining a realistic classification model, we propose the use of abstracts summarised in relevant sentences as unlabelled examples through Self-Training. The best model achieves 84% accuracy and 0.84 F1 score on our dataset" @default.
- W2886342253 created "2018-08-22" @default.
- W2886342253 creator A5013327917 @default.
- W2886342253 creator A5055236937 @default.
- W2886342253 creator A5084744703 @default.
- W2886342253 date "2018-01-01" @default.
- W2886342253 modified "2023-09-24" @default.
- W2886342253 title "Identifying Key Sentences for Precision Oncology Using Semi-Supervised Learning" @default.
- W2886342253 cites W1515842608 @default.
- W2886342253 cites W1596077776 @default.
- W2886342253 cites W1630959083 @default.
- W2886342253 cites W1825821140 @default.
- W2886342253 cites W1832693441 @default.
- W2886342253 cites W1972119323 @default.
- W2886342253 cites W1996211074 @default.
- W2886342253 cites W2050871273 @default.
- W2886342253 cites W2059733647 @default.
- W2886342253 cites W2080558111 @default.
- W2886342253 cites W2101390659 @default.
- W2886342253 cites W2101746535 @default.
- W2886342253 cites W2123958887 @default.
- W2886342253 cites W2132442585 @default.
- W2886342253 cites W2133227149 @default.
- W2886342253 cites W2134510195 @default.
- W2886342253 cites W2147994374 @default.
- W2886342253 cites W2148008364 @default.
- W2886342253 cites W2149684865 @default.
- W2886342253 cites W2154455818 @default.
- W2886342253 cites W2174775663 @default.
- W2886342253 cites W2251738044 @default.
- W2886342253 cites W2284289336 @default.
- W2886342253 cites W2442495973 @default.
- W2886342253 cites W2484269232 @default.
- W2886342253 cites W2582630951 @default.
- W2886342253 cites W2595767595 @default.
- W2886342253 cites W2734608416 @default.
- W2886342253 cites W2743354079 @default.
- W2886342253 cites W2962684696 @default.
- W2886342253 cites W2964046515 @default.
- W2886342253 cites W2964182988 @default.
- W2886342253 doi "https://doi.org/10.18653/v1/w18-2305" @default.
- W2886342253 hasPublicationYear "2018" @default.
- W2886342253 type Work @default.
- W2886342253 sameAs 2886342253 @default.
- W2886342253 citedByCount "4" @default.
- W2886342253 countsByYear W28863422532020 @default.
- W2886342253 countsByYear W28863422532021 @default.
- W2886342253 countsByYear W28863422532022 @default.
- W2886342253 countsByYear W28863422532023 @default.
- W2886342253 crossrefType "proceedings-article" @default.
- W2886342253 hasAuthorship W2886342253A5013327917 @default.
- W2886342253 hasAuthorship W2886342253A5055236937 @default.
- W2886342253 hasAuthorship W2886342253A5084744703 @default.
- W2886342253 hasBestOaLocation W28863422531 @default.
- W2886342253 hasConcept C119857082 @default.
- W2886342253 hasConcept C121608353 @default.
- W2886342253 hasConcept C126322002 @default.
- W2886342253 hasConcept C154945302 @default.
- W2886342253 hasConcept C204321447 @default.
- W2886342253 hasConcept C26517878 @default.
- W2886342253 hasConcept C3020497934 @default.
- W2886342253 hasConcept C38652104 @default.
- W2886342253 hasConcept C41008148 @default.
- W2886342253 hasConcept C71924100 @default.
- W2886342253 hasConceptScore W2886342253C119857082 @default.
- W2886342253 hasConceptScore W2886342253C121608353 @default.
- W2886342253 hasConceptScore W2886342253C126322002 @default.
- W2886342253 hasConceptScore W2886342253C154945302 @default.
- W2886342253 hasConceptScore W2886342253C204321447 @default.
- W2886342253 hasConceptScore W2886342253C26517878 @default.
- W2886342253 hasConceptScore W2886342253C3020497934 @default.
- W2886342253 hasConceptScore W2886342253C38652104 @default.
- W2886342253 hasConceptScore W2886342253C41008148 @default.
- W2886342253 hasConceptScore W2886342253C71924100 @default.
- W2886342253 hasLocation W28863422531 @default.
- W2886342253 hasOpenAccess W2886342253 @default.
- W2886342253 hasPrimaryLocation W28863422531 @default.
- W2886342253 hasRelatedWork W2151447942 @default.
- W2886342253 hasRelatedWork W2329452785 @default.
- W2886342253 hasRelatedWork W2356380379 @default.
- W2886342253 hasRelatedWork W2611614995 @default.
- W2886342253 hasRelatedWork W2961085424 @default.
- W2886342253 hasRelatedWork W3046775127 @default.
- W2886342253 hasRelatedWork W4286629047 @default.
- W2886342253 hasRelatedWork W4306321456 @default.
- W2886342253 hasRelatedWork W4306674287 @default.
- W2886342253 hasRelatedWork W4224009465 @default.
- W2886342253 isParatext "false" @default.
- W2886342253 isRetracted "false" @default.
- W2886342253 magId "2886342253" @default.
- W2886342253 workType "article" @default.