@inProceedings{Borin-Lars2010-118907, title = {Diabase: Towards a diachronic BLARK in support of historical studies}, booktitle = {Proceedings of LREC 2010}, author = {Borin, Lars and Forsberg, Markus and Kokkinakis, Dimitrios}, year = {2010}, } @inProceedings{Kokkinakis-Dimitrios2010-113194, title = {A Swedish Scientific Medical Corpus for Terminology Management and Linguistic Exploration}, abstract = {This paper describes the development of a new Swedish scientific medical corpus. We provide a detailed description of the characteristics of this new collection as well results for a number of term management tasks, including terminology validation and terminology extraction based on this material. Although the corpus is representative for the scientific medical domain it still covers a lot of specialised sub-disciplines such as “diabetes” and “osteoporosis” which makes it suitable for facilitating the production of smaller and more focused subcorpora. We have tried to address this issue by making explicit some features of the corpus in order to demonstrate the corpus usefulness particularly for the quality assessment of official terminologies such as the Systematized NOmenclature of MEDicine - Clinical Terms (SNOMED CT).}, booktitle = {Proceedings of the 7th international conference on Language Resources and Evaluation (LREC), Malta}, author = {Kokkinakis, Dimitrios and Gerdin, Ulla}, year = {2010}, } @inProceedings{Kokkinakis-Dimitrios2010-119441, title = {Linking SweFN++ with Medical Resources, towards a MedFrameNet for Swedish}, abstract = {In this pilot study we define and apply a methodology for building an event extraction system for the Swedish scientific medical and clinical language. Our aim is to find and describe linguistic expressions which refer to medical events, such as events related to diseases, symptoms and drug effects. In order to achieve this goal we have initiated actions that aim to extend and refine parts of the ongoing compilation of the Swedish FrameNet++ (SFN++), which, as its English original predecessor, is grounded in Frame Semantics which provides a sound theoretical ground for modeling and linking linguistic structures encountered in general language and in specific domains (after specialization). Using such resource we manually annotate domain texts to be used as training data for automatic event extraction by automated techniques.}, booktitle = {Proceedings of the Second Louhi Workshop on Text and Data Mining of Health Documents. A NAACL-HTL Workshop}, author = {Kokkinakis, Dimitrios and Toporowska Gronostaj, Maria}, year = {2010}, } @inProceedings{Kokkinakis-Dimitrios2010-119444, title = {Korpus för vårdens och omsorgens fackspråk.}, abstract = {Inom ramen för regeringens satsning ”Nationell IT-strategi för vård och omsorg” har Socialstyrelsen fått i uppdrag att översätta och anpassa begreppssystemet ’the Systematized Nomenclature of Medicine, Clinical Terms’ till svenska. Med hjälp av Läkartidningens digitala arkiv har vi utvecklat metoder för att effektivisera kvalitetssäkringen av terminnehållet. }, booktitle = {Humanistdagen 2010 - humaniora i dagens samhälle.}, author = {Kokkinakis, Dimitrios}, year = {2010}, } @article{Kokkinakis-Dimitrios2010-120480, title = {Läkartidningens arkiv i en ny skepnad - En resurs för forskare, läkare och allmänhet}, abstract = {I Sverige har det tagits fram en medicinsk korpus baserad på Läkartidningens digitala arkiv. Denna resurs möjliggör precisa sökningar och värdefull tillgång till medicinsk terminologisk information på olika nivåer. Dimitrios Kokkinakis från Göteborgs universitet och Ulla Gerdin från Socialstyrelsen presenterar projektet. }, author = {Kokkinakis, Dimitrios and Gerdin, Ulla}, year = {2010}, volume = {1/2010}, pages = {22--28}, } @inProceedings{Borin-Lars2010-110368, title = {The past meets the present in Swedish FrameNet++}, abstract = {The paper is about a recently initiated project which aims at the development of a Swedish FrameNet as an integral part of a larger lexical resource, hence the name “Swedish FrameNet++” (SweFN++). It focuses on reuse of free electronic resources and their role in the acquisition and population of Swedish frames. After a brief overview of Swedish resources, we reflect on three approaches to recycling the available lexical data in a semi-automatic manner. SweFN++ will be a multi-functional resource supporting research within lexicology and linguistics as well as different applications within computational lexicography and language technology, not to mention e-science.}, booktitle = {14th EURALEX International Congress}, author = {Borin, Lars and Dannélls, Dana and Forsberg, Markus and Toporowska Gronostaj, Maria and Kokkinakis, Dimitrios}, year = {2010}, pages = {269--281}, } @incollection{Borin-Lars2010-124517, title = {Literary onomastics and language technology}, booktitle = {Literary education and digital learning}, author = {Borin, Lars and Kokkinakis, Dimitrios}, year = {2010}, publisher = {Information Science Reference}, adress = {Hershey - New York}, ISBN = {978-1-60566-932-8}, pages = {53--78}, } @inProceedings{Allvin-H.2010-120479, title = {Characteristics and Analysis of Finnish and Swedish Clinical Intensive Care Nursing Narratives}, abstract = {We present a comparative study of Finnish and Swedish free-text nursing narratives from intensive care. Although the two languages are linguistically very dissimilar, our hypothesis is that there are similarities that are important and interesting from a language technology point of view. This may have implications when building tools to support producing and using health care documentation. We perform a comparative qualitative analysis based on structure and content, as well as a comparative quantitative analysis on Finnish and Swedish Intensive Care Unit (ICU) nursing narratives. Our findings are that ICU nursing narratives in Finland and Sweden have many properties in common, but that many of these are challenging when it comes to developing language technology tools. }, booktitle = {Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents}, author = {Allvin, H. and Carlsson, E. and Dalianis, H. and Danielsson-Ojala, R. and Daudaravicius, V. and Hassel, M. and Kokkinakis, Dimitrios and Lundgren-Laine, H. and Nilsson, G. and Nytrø, Ø. and Salanterä, S. and Skeppstedt, M. and Suominen, H. and Velupillai, S.}, year = {2010}, pages = {53 -- 60}, } @article{Kokkinakis-Dimitrios2010-125644, title = {Complementary Methods for De-identifying Sensitive Data with a focus on Clinical Discourse}, abstract = {In the era of the Electronic Health Record (EHR) the release of individual data for research, public health planning, health care statistics, monitoring of diagnostic tests, automated data collection for health care registries and tracking disease outbreaks are some of the areas in which the protection of Personal Health Information (PHI) has become an important concern. The purpose of this study is to adapt and apply synergetic methods to document de-identification, particularly clinical, or other sources of sensitive data. The main challenge and goal of this research is to retain important concepts and PHI in the documents in a standardized and neutral manner as means of encryption without violating the integrity of the PHI and without sacrificing the quality and intended meaning of the authors.}, author = {Kokkinakis, Dimitrios}, year = {2010}, volume = {45}, pages = {243--246}, } @article{Borin-Lars2010-129126, title = {Swedish FrameNet++}, author = {Borin, Lars and Dannélls, Dana and Forsberg, Markus and Toporowska Gronostaj, Maria and Kokkinakis, Dimitrios}, year = {2010}, } @article{Kokkinakis-Dimitrios2010-130212, title = {Is data scrubbing useful for anonymizing sensitive data?.}, abstract = {The release of individual data for research, public health planning, health care statistics, monitoring of diagnostic tests, automated data collection for health care registries and tracking disease outbreaks are some of the areas in which the protection of Personal Health Information (PHI) has become an important concern. The purpose of this study is to adapt and apply synergetic methods to document de-identification, particularly in the clinical setting. The main challenge is to retain important concepts and PHI in the documents in a standardized and neutral manner as means of encryption without violating the integrity of the PHI and without sacrificing the quality and intended meaning of the authors.}, author = {Kokkinakis, Dimitrios}, year = {2010}, } @article{Kokkinakis-Dimitrios2010-130213, title = {Är "data scrubbing" en användbar metod för att anonymisera känsliga patientdata?.}, abstract = {De senaste årens ökande användning av modern informationsteknik inom sjukvården har medfört en kraftig ökning av elektronisk dokumentation som rör patientens hälsotillstånd, vård och behandling. Vårddokumentationen blir både mer detaljerad och mer individuell, samtidigt som den uppdateras och förändras regelbundet. Patientjournalen är i första hand till för att bidra till en god och säker vård av patienten, men också en viktig informationskälla för FoU. Ett stort hinder för utnyttjandet av journalinformation som forskningskälla är de etiska och rättsliga problemen. För att kunna hantera och utnyttja dessa stora och ständigt växande informationsmängder ställs därmed högre krav på säker, skyddad och effektiv informationshantering.}, author = {Kokkinakis, Dimitrios}, year = {2010}, } @article{Kokkinakis-Dimitrios2010-130210, title = {Initiala resultat av en storskalig automatisk indexering av vetenskaplig litteratur med hela det svenska SNOMED CT - problem och möjligheter.}, abstract = {Syftet med denna studie är dels att skapa en stor samling svenska medicinska elektroniska texter, en korpus, och dels att validera och kvalitetssäkra existerande termer ur SNOMED CT (the Systematized NOmenclature of MEDicine - Clinical Terms) gentemot korpusinnehållet. På det sättet kan man få en objektiv uppfattning om SNOMED CT:s validitet, täckning och reliabilitet. Man kan även berika terminologin med nya termer eller termvarianter genom att automatiskt extrahera termkandidater inom olika delfackområden från korpusen med hjälp av olika statistiska och lingvistiska metoder. Resultat av de korpusbaserade, empiriska studierna ska kunna användas av terminologer i deras arbete med att göra SNOMED CT mer täckande, pålitlig och enhetlig. Samtidigt, genom användning av autentisk data, kan man försäkra sig om att termvarianterna (existerande eller nya) är vedertagna termer hos fackmän. I fall flera etablerade termvarianter (nya termkandidater) förekommer i korpusen kan dessa införas efter manuell granskning som synonymer till rekommenderade termer (med stöd av ett lämpligt granskningsgränssnitt) och därmed vidare utveckla innehållet i SNOMED CT. Följaktligen kommer vår presentation att innehålla en redovisning som bygger på tre huvudpelare – korpusuppbyggnad – termvalidering – termextrahering. Korpusen samlades in från två källor efter erhållet tillstånd. Texternas ursprung i korpusen kommer dels från Läkartidningens (LT) digitala arkiv och dels från DiabetologNytts (DN) digitala arkiv .}, author = {Kokkinakis, Dimitrios}, year = {2010}, }