FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2103893317> ?p ?o ?g. }

• W2103893317 endingPage "3185" @default.
• W2103893317 startingPage "3179" @default.
• W2103893317 abstract "Abstract Motivation: Many practical tasks in biomedicine require accessing specific types of information in scientific literature; e.g. information about the methods, results or conclusions of the study in question. Several approaches have been developed to identify such information in scientific journal articles. The best of these have yielded promising results and proved useful for biomedical text mining tasks. However, relying on fully supervised machine learning (ml) and a large body of annotated data, existing approaches are expensive to develop and port to different tasks. A potential solution to this problem is to employ weakly supervised learning instead. In this article, we investigate a weakly supervised approach to identifying information structure according to a scheme called Argumentative Zoning (az). We apply four weakly supervised classifiers to biomedical abstracts and evaluate their performance both directly and in a real-life scenario in the context of cancer risk assessment. Results: Our best weakly supervised classifier (based on the combination of active learning and self-training) performs well on the task, outperforming our best supervised classifier: it yields a high accuracy of 81% when just 10% of the labeled data is used for training. When cancer risk assessors are presented with the resulting annotated abstracts, they find relevant information in them significantly faster than when presented with unannotated abstracts. These results suggest that weakly supervised learning could be used to improve the practical usefulness of information structure for real-life tasks in biomedicine. Availability: The annotated dataset, classifiers and the user test for cancer risk assessment are available online at http://www.cl.cam.ac.uk/~yg244/11bioinfo.html. Contact: anna.korhonen@cl.cam.ac.uk" @default.
• W2103893317 created "2016-06-24" @default.
• W2103893317 creator A5018249303 @default.
• W2103893317 creator A5036940014 @default.
• W2103893317 creator A5046293601 @default.
• W2103893317 creator A5081393566 @default.
• W2103893317 date "2011-09-22" @default.
• W2103893317 modified "2023-10-04" @default.
• W2103893317 title "Weakly supervised learning of information structure of scientific abstracts—is it accurate enough to benefit real-world tasks in biomedicine?" @default.
• W2103893317 cites W1604214695 @default.
• W2103893317 cites W1972978214 @default.
• W2103893317 cites W1993202648 @default.
• W2103893317 cites W2001829063 @default.
• W2103893317 cites W2004761926 @default.
• W2103893317 cites W2019575783 @default.
• W2103893317 cites W2022023435 @default.
• W2103893317 cites W2051669046 @default.
• W2103893317 cites W2053154970 @default.
• W2103893317 cites W2080021732 @default.
• W2103893317 cites W2084413241 @default.
• W2103893317 cites W2107141268 @default.
• W2103893317 cites W2120587524 @default.
• W2103893317 cites W2120879767 @default.
• W2103893317 cites W2121678130 @default.
• W2103893317 cites W2133990480 @default.
• W2103893317 cites W2145003932 @default.
• W2103893317 cites W2146737815 @default.
• W2103893317 cites W2146777297 @default.
• W2103893317 cites W2162152253 @default.
• W2103893317 cites W2167277498 @default.
• W2103893317 cites W2442495973 @default.
• W2103893317 cites W4252684946 @default.
• W2103893317 doi "https://doi.org/10.1093/bioinformatics/btr536" @default.
• W2103893317 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/21949269" @default.
• W2103893317 hasPublicationYear "2011" @default.
• W2103893317 type Work @default.
• W2103893317 sameAs 2103893317 @default.
• W2103893317 citedByCount "16" @default.
• W2103893317 countsByYear W21038933172012 @default.
• W2103893317 countsByYear W21038933172013 @default.
• W2103893317 countsByYear W21038933172014 @default.
• W2103893317 countsByYear W21038933172015 @default.
• W2103893317 countsByYear W21038933172016 @default.
• W2103893317 countsByYear W21038933172017 @default.
• W2103893317 countsByYear W21038933172018 @default.
• W2103893317 countsByYear W21038933172019 @default.
• W2103893317 countsByYear W21038933172021 @default.
• W2103893317 countsByYear W21038933172022 @default.
• W2103893317 crossrefType "journal-article" @default.
• W2103893317 hasAuthorship W2103893317A5018249303 @default.
• W2103893317 hasAuthorship W2103893317A5036940014 @default.
• W2103893317 hasAuthorship W2103893317A5046293601 @default.
• W2103893317 hasAuthorship W2103893317A5081393566 @default.
• W2103893317 hasBestOaLocation W21038933171 @default.
• W2103893317 hasConcept C119857082 @default.
• W2103893317 hasConcept C136389625 @default.
• W2103893317 hasConcept C154945302 @default.
• W2103893317 hasConcept C41008148 @default.
• W2103893317 hasConcept C50644808 @default.
• W2103893317 hasConcept C60644358 @default.
• W2103893317 hasConcept C66782513 @default.
• W2103893317 hasConcept C86803240 @default.
• W2103893317 hasConcept C95623464 @default.
• W2103893317 hasConceptScore W2103893317C119857082 @default.
• W2103893317 hasConceptScore W2103893317C136389625 @default.
• W2103893317 hasConceptScore W2103893317C154945302 @default.
• W2103893317 hasConceptScore W2103893317C41008148 @default.
• W2103893317 hasConceptScore W2103893317C50644808 @default.
• W2103893317 hasConceptScore W2103893317C60644358 @default.
• W2103893317 hasConceptScore W2103893317C66782513 @default.
• W2103893317 hasConceptScore W2103893317C86803240 @default.
• W2103893317 hasConceptScore W2103893317C95623464 @default.
• W2103893317 hasIssue "22" @default.
• W2103893317 hasLocation W21038933171 @default.
• W2103893317 hasLocation W21038933172 @default.
• W2103893317 hasOpenAccess W2103893317 @default.
• W2103893317 hasPrimaryLocation W21038933171 @default.
• W2103893317 hasRelatedWork W2556319748 @default.
• W2103893317 hasRelatedWork W2623427976 @default.
• W2103893317 hasRelatedWork W2961085424 @default.
• W2103893317 hasRelatedWork W3162567751 @default.
• W2103893317 hasRelatedWork W3200179079 @default.
• W2103893317 hasRelatedWork W3210156800 @default.
• W2103893317 hasRelatedWork W4221088574 @default.
• W2103893317 hasRelatedWork W4226172683 @default.
• W2103893317 hasRelatedWork W4249229055 @default.
• W2103893317 hasRelatedWork W4285260836 @default.
• W2103893317 hasVolume "27" @default.
• W2103893317 isParatext "false" @default.
• W2103893317 isRetracted "false" @default.
• W2103893317 magId "2103893317" @default.
• W2103893317 workType "article" @default.