BibSonomy bookmarks for /tag/myownhttps://www.bibsonomy.org/tag/myownBibSonomy RSS Feed for /tag/myownQuadrato lapide (RSA 2024) - EklogaiMaterial for a Renaissance Society of America 2024 annual meeting paperhttp://croala.ffzg.unizg.hr/eklogai/quadrato-rsa-2024/filologanoga2024-03-05T19:37:59+01:00architectura laudationes-urbium myown neo-latin <span itemprop="description">Material for a Renaissance Society of America 2024 annual meeting paper</span>Folge 11 – Wörter zählen, oder: Die Top 10 von Goethes Substantiven, Verben und Adjektiven. Was geben die Datenbanken her? – Goethe-Gesellschaft in Weimar e.V.https://www.goethe-gesellschaft.de/podcast/folge-11-woerter-zaehlen-oder-die-top-10-von-goethes-substantiven-verben-und-adjektiven-was-geben-die-datenbanken-her/jaeschke2024-02-09T17:25:39+01:00dh goethe myown nlp podcast <a itemprop="url" data-versiondate="2024-02-09T17:25:39+01:00" href="https://www.goethe-gesellschaft.de/podcast/folge-11-woerter-zaehlen-oder-die-top-10-von-goethes-substantiven-verben-und-adjektiven-was-geben-die-datenbanken-her/" rel="nofollow" class="description-link">https://www.goethe-gesellschaft.de/podcast/folge-11-woerter-zaehlen-oder-die-top-10-von-goethes-substantiven-verben-und-adjektiven-was-geben-die-datenbanken-her/</a>Antigonin najteži koncept: filia. Razgovor s Nevenom Jovanovićemhttps://hrcak.srce.hr/clanak/426370filologanoga2024-01-03T20:09:53+01:00Antigona greek greekTragedy myown <a itemprop="url" data-versiondate="2024-01-03T20:09:53+01:00" href="https://hrcak.srce.hr/clanak/426370" rel="nofollow" class="description-link">https://hrcak.srce.hr/clanak/426370</a>Maruli autographi Latini - Eklogaihttps://croala.ffzg.unizg.hr/eklogai/neolatina/maruli-autographi-latini/filologanoga2024-01-03T19:14:49+01:00markoMarulić myown <a itemprop="url" data-versiondate="2024-01-03T19:14:49+01:00" href="https://croala.ffzg.unizg.hr/eklogai/neolatina/maruli-autographi-latini/" rel="nofollow" class="description-link">https://croala.ffzg.unizg.hr/eklogai/neolatina/maruli-autographi-latini/</a>Digital Humanities and students of LatinSlides for the talk "Introducing Digital Humanities to students of Latin", Freiburg, 29. Sep 2023, (Digitale) Chancen für den Lateinunterrichthttp://croala.ffzg.unizg.hr/dhlatein/filologanoga2023-09-27T10:00:35+02:00digitalHumanities latinLanguage myown nastava teaching <span itemprop="description">Slides for the talk "Introducing Digital Humanities to students of Latin", Freiburg, 29. Sep 2023, (Digitale) Chancen für den Lateinunterricht</span>Digital Humanities and students of LatinSlides for the talk "Introducing Digital Humanities to students of Latin", Freiburg, 29. Sep 2023, (Digitale) Chancen für den Lateinunterrichthttp://croala.ffzg.unizg.hr/dhlatein/#/title-slidefilologanoga2023-09-27T10:00:25+02:00digitalHumanities latinLanguage myown nastava teaching <span itemprop="description">Slides for the talk "Introducing Digital Humanities to students of Latin", Freiburg, 29. Sep 2023, (Digitale) Chancen für den Lateinunterricht</span>CroRIS - Osobe: Neven JovanovicCroRIS znanstvena bibliografijahttps://www.croris.hr/osobe/profil/6338filologanoga2023-08-13T11:59:46+02:00myown <span itemprop="description">CroRIS znanstvena bibliografija</span>OSF Preprints | An entangled dragon in a Renaissance inscription from Dalmatiahttps://osf.io/t82q6filologanoga2023-07-01T12:59:12+02:00dalmatia markoMarulić myown split <a itemprop="url" data-versiondate="2023-07-01T12:59:12+02:00" href="https://osf.io/t82q6" rel="nofollow" class="description-link">https://osf.io/t82q6</a>Ontology-driven and weakly supervised rare disease identification from clinical notes | BMC Medical Informatics and Decision Making | Full TextComputational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due to few cases available for machine learning and the need for data annotation from domain experts. We propose a method using ontologies and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT). The ontology-driven framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by contextually linking mentions to concepts in Unified Medical Language System (UMLS), with a Named Entity Recognition and Linking (NER+L) tool, SemEHR, and weak supervision with customised rules and contextual mention representation; (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). The weakly supervised approach is proposed to learn a phenotype confirmation model to improve Text-to-UMLS linking, without annotated data from domain experts. We evaluated the approach on three clinical datasets, MIMIC-III discharge summaries, MIMIC-III radiology reports, and NHS Tayside brain imaging reports from two institutions in the US and the UK, with annotations. The improvements in the precision were pronounced (by over 30% to 50% absolute score for Text-to-UMLS linking), with almost no loss of recall compared to the existing NER+L tool, SemEHR. Results on radiology reports from MIMIC-III and NHS Tayside were consistent with the discharge summaries. The overall pipeline processing clinical notes can extract rare disease cases, mostly uncaptured in structured data (manually assigned ICD codes). The study provides empirical evidence for the task by applying a weakly supervised NLP pipeline on clinical notes. The proposed weak supervised deep learning approach requires no human annotation except for validation and testing, by leveraging ontologies, NER+L tools, and contextual representations. The study also demonstrates that Natural Language Processing (NLP) can complement traditional ICD-based approaches to better estimate rare diseases in clinical notes. We discuss the usefulness and limitations of the weak supervision approach and propose directions for future studies.https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-023-02181-9hangdong2023-05-06T09:33:08+02:00clinical-nlp data-annotations ehr entity-linking mimic-iii myown nhs nlp ontologies ontology-matching ordo phenotyping radiology-reports rare-diseases scotland tayside-nhs text-phenotying umls <span itemprop="description">Computational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due to few cases available for machine learning and the need for data annotation from domain experts. We propose a method using ontologies and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT). The ontology-driven framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by contextually linking mentions to concepts in Unified Medical Language System (UMLS), with a Named Entity Recognition and Linking (NER+L) tool, SemEHR, and weak supervision with customised rules and contextual mention representation; (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). The weakly supervised approach is proposed to learn a phenotype confirmation model to improve Text-to-UMLS linking, without annotated data from domain experts. We evaluated the approach on three clinical datasets, MIMIC-III discharge summaries, MIMIC-III radiology reports, and NHS Tayside brain imaging reports from two institutions in the US and the UK, with annotations. The improvements in the precision were pronounced (by over 30% to 50% absolute score for Text-to-UMLS linking), with almost no loss of recall compared to the existing NER+L tool, SemEHR. Results on radiology reports from MIMIC-III and NHS Tayside were consistent with the discharge summaries. The overall pipeline processing clinical notes can extract rare disease cases, mostly uncaptured in structured data (manually assigned ICD codes). The study provides empirical evidence for the task by applying a weakly supervised NLP pipeline on clinical notes. The proposed weak supervised deep learning approach requires no human annotation except for validation and testing, by leveraging ontologies, NER+L tools, and contextual representations. The study also demonstrates that Natural Language Processing (NLP) can complement traditional ICD-based approaches to better estimate rare diseases in clinical notes. We discuss the usefulness and limitations of the weak supervision approach and propose directions for future studies.</span>BDCC | Free Full-Text | Federated Learning to Safeguard Patients Data: A Medical Image Retrieval Casehttps://www.mdpi.com/2504-2289/7/1/18mfisichella2023-02-14T09:42:20+01:00myown <a itemprop="url" data-versiondate="2023-02-14T09:42:20+01:00" href="https://www.mdpi.com/2504-2289/7/1/18" rel="nofollow" class="description-link">https://www.mdpi.com/2504-2289/7/1/18</a>A Graph-Based Approach to Detect Anomalies Based on Shared Attribute Values | SpringerLinkhttps://link.springer.com/chapter/10.1007/978-3-031-24801-6_36mfisichella2023-02-14T09:42:04+01:00myown <a itemprop="url" data-versiondate="2023-02-14T09:42:04+01:00" href="https://link.springer.com/chapter/10.1007/978-3-031-24801-6_36" rel="nofollow" class="description-link">https://link.springer.com/chapter/10.1007/978-3-031-24801-6_36</a>IEEE Xplore Full-Text PDF:https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10038326mfisichella2023-02-14T09:41:46+01:00myown <a itemprop="url" data-versiondate="2023-02-14T09:41:46+01:00" href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10038326" rel="nofollow" class="description-link">https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10038326</a>A survey on clinical natural language processing in the United Kingdom from 2007 to 2022 | npj Digital MedicineMuch of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union’s funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP’s great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.https://www.nature.com/articles/s41746-022-00730-6hangdong2022-12-24T19:15:54+01:00clinical_nlp hdruk health_infomatics medical-informatics myown natural-language-processing nlp nlp_applications review scientometrics survey text-analytics uk <span itemprop="description">Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union’s funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP’s great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.</span>Complexity in Ancient Greek sentenceStart page for analysis of an Ancient Greek treebank sethttps://croala.ffzg.unizg.hr/basex/greek-complexityfilologanoga2022-10-16T20:46:44+02:00digitalHumanities greek grčki myown openPhilology <span itemprop="description">Start page for analysis of an Ancient Greek treebank set</span>FCA4DHFormal Concept Analysis for Digital Humanities
https://fca4dh.algebra20.de/tomhanika2022-09-22T22:37:41+02:00algebra concept dh digital fca formal humanities myown <span itemprop="description">Formal Concept Analysis for Digital Humanities
</span>FCA4DHFormal Concept Analysis for Digital Humanities
https://fca4dh.algebra20.de/jaeschke2022-09-22T16:28:04+02:00algebra analysis concept dh digital fca formal humanities myown <span itemprop="description">Formal Concept Analysis for Digital Humanities
</span>OSF Preprints | Preparing a research corpus of Stanislaus Kostka plays (handout)Jovanovic, N. (2022, August 31). Preparing a research corpus of Stanislaus Kostka plays (handout). Retrieved from osf.io/6wfpnhttps://osf.io/6wfpnfilologanoga2022-08-31T22:25:06+02:00kostkaDrama myown neoLatinDrama <span itemprop="description">Jovanovic, N. (2022, August 31). Preparing a research corpus of Stanislaus Kostka plays (handout). Retrieved from osf.io/6wfpn</span>OSF Preprints | Specimen editionis criticae digitalis: Nicolai episcopi Modrussiensis oratio de funere Petri cardinalis S. Sixti (1474)https://osf.io/fsgj3/filologanoga2022-07-31T21:11:40+02:00digitalHumanities myown nikolamodruški <a itemprop="url" data-versiondate="2022-07-31T21:11:40+02:00" href="https://osf.io/fsgj3/" rel="nofollow" class="description-link">https://osf.io/fsgj3/</a>Rukopisi, kolacija svjedoka predaje i paratekstovi nadgrobnog govora Nikole Modruškog za kardinala Pietra Riarija (1474)Rad iznosi najvažnije podatke o rukopisnim izvorima latinskog govora Nikole Modruškog za kardinala Pietra Riarija (nakon 18. siječnja 1474). Potom se izvještava o rezultatima kolacije trinaest poznatih izvora predaje teksta (tiskanih izdanja i rukopi...https://hrcak.srce.hr/241119filologanoga2022-07-30T22:44:47+02:00manuscript myown nikolamodruški rukopis <span itemprop="description">Rad iznosi najvažnije podatke o rukopisnim izvorima latinskog govora Nikole Modruškog za kardinala Pietra Riarija (nakon 18. siječnja 1474). Potom se izvještava o rezultatima kolacije trinaest poznatih izvora predaje teksta (tiskanih izdanja i rukopi...</span>Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching | ZenodoThe purpose of these datasets is to support equivalence and subsumption ontology matching. There are five ontology pairs extracted from MONDO and UMLS: Source Ontology Pair Category MONDO OMIM-ORDO Disease MONDO NCIT-DOID Disease UMLS SNOMED-FMA Body UMLS SNOMED-NCIT Pharm UMLS SNOMED-NCIT Neoplas Each pair is associated with three folders: "raw_data", "equiv_match", and "subs_match", corresponding to the downloaded source ontologies, the package for equivalence matching, and the package for subsumption matching. See detailed documentation at: https://krr-oxford.github.io/DeepOnto/#/om_resources. See the incoming OAEI Bio-ML track at: https://www.cs.ox.ac.uk/isg/projects/ConCur/oaei/. See our resource paper at: https://arxiv.org/abs/2205.03447.https://zenodo.org/record/6516125#.YsmBUcHML-0hangdong2022-07-09T15:25:28+02:00dataset iswc machine_learning myown oaei om ontology ontology_matching <span itemprop="description">The purpose of these datasets is to support equivalence and subsumption ontology matching. There are five ontology pairs extracted from MONDO and UMLS: Source Ontology Pair Category MONDO OMIM-ORDO Disease MONDO NCIT-DOID Disease UMLS SNOMED-FMA Body UMLS SNOMED-NCIT Pharm UMLS SNOMED-NCIT Neoplas Each pair is associated with three folders: "raw_data", "equiv_match", and "subs_match", corresponding to the downloaded source ontologies, the package for equivalence matching, and the package for subsumption matching. See detailed documentation at: https://krr-oxford.github.io/DeepOnto/#/om_resources. See the incoming OAEI Bio-ML track at: https://www.cs.ox.ac.uk/isg/projects/ConCur/oaei/. See our resource paper at: https://arxiv.org/abs/2205.03447.</span>