A paper written by Edephonce N. Nfuka (The Open University of Tanzania, Tanzania) and Lazar Rusu (Stockholm University, Sweden), entitled: “Critical Success Framework for Implementing Effective IT Governance in Tanzanian Public Sector Organizations “ has been accepted for publication in the Journal of Global Information Technology Management (JGITM), Vol.16, No. 3, July 2013, Ivy League Publishing. The Journal of Global Information Technology Management (JGITM) (http://jgitm.uncg.edu/) is a high quality international journal which addresses international issues of IT management. JGITM is the premier journal in Global IT and is included in Social Sciences Citation Index (SSCI).
The EnRiMa project successfully completed the second review
A part of the EnRiMa system demonstrated in Brussels
The EnRiMa project partners gathered in Brussels 29-30 May to have the projects second review meeting. During the review meeting the prototype of the EnRiMa decisions support system was demonstrated for the reviewers. It was demonstrated how the system based on information about a building, such as existing heating equipment and inner volumes, could calculate the optimal way to manage the building. Furthermore it was demonstrated how the system could collect data from external systems, such as weather forecast providers and installed building management systems. A part of the team that demonstrated the system in Brussels was SysLab members Martin Henkel and Janis Stirna. The SysLab team also includes Wayne Westmoreland that together with Martin has worked on the implementation of the system. The EnRiMa project (Energy Efficiency and Risk Management in Public Buildings) is a European Commission funded collaboration between Stockholm University, University College London, International Institute for Applied Systems Analysis, Universidad Rey Juan Carlos, Minerva Consulting and Communication, SINTEF Group, Tecnalia, and Hidrocantábrico Energía.
Project website: http://www.enrima-project.eu/
IS-seminar: Jörg Tiedemann about Machine Translation for Under-Resourced Languages and Domains
Last week, Jörg Tiedemann gave an IS-seminar on “Machine Translation for Under-Resourced Languages and Domains”. Jörg Tiedemann is a visiting Professor at the Department of Linguistics and Philology at Uppsala University, doing research in parallel corpora and machine translation. He is probably best know at DSV for Uplug, a collection of tools for processing parallel corpora, which has been used in several DSV student thesis projects.
The main topic of the seminar was how a closely related language can be of use for an under-resourced language, or for an under-resourced domain of a language. For statistical machine translation between two languages, you need parallel corpora, that is original and translated texts in these two languages. This does not always exist, especially not in the domain you need, and in those cases you can use an intermediate language. There are for instance many legal texts that exist both in an English and a Danish version (since both countries are in the EU), whereas there are not that many for the language pairs English/Norwegian. Standard machine translation techniques, using word alignment, can be used for constructing a machine translation system between English and Danish. To translate between Norwegian and Danish, a new method in form of character alignment, is instead used. Thereby, Danish can be used as an intermediate language for creating automatic translations between English and Norwegian.
Jörg Tiedemann
Southern California Workshop on Medical Text Analysis and Visualization
Aron Henriksson and Maria Skeppstedt presented at the Southern California Workshop on Medical Text Analysis and Visualization during their visit at the Division of Biomedical Informatics, University of California, San Diego. There were many interesting presentations at the workshop, which also led to interesting discussions. The presentation topics most closely related to what is being done in our Clinical Text Mining Group at DSV were “Using Twitter to examine smoking behaviour & tobacco products” by Mike Conway (Division of Biomedical Informatics, UCSD), “Encoding Semantic and Discourse Features for Problem List Generation” by Danielle Mowery (Division of Biomedical Informatics, UCSD) and “Evidence-based Reduction of Perceived and Actual Text Difficulty Using Natural Language Processing” by Gondy Leroy (School of Information Systems & Technology Claremont Graduate University), all of them giving much useful input to our current projects.
Inspiring talks were also given by the other speakers, giving new ideas to text mining and visualisation approaches, e.g. by Andre Skupin (Department of Geography, SDSU) who talked about “Visualizing the topical structure of the medical sciences: A self-organizing
map approach” and Ricky Taira (Department of Radiological Sciences, UCLA) who talked about “Defining and organizing medical NLP tasks”.
Aron talking about automatic synonym extraction using random indexing
Maria talking about features for named entity recognition
Two newly appointed associate professors
Congratulations to our two newly appointed associate professors Jelena Zdravkovic and Åsa Smedberg both at IS-enheten, well done!
/Hercules
Research Visit at UC San Diego
Maria Skeppstedt and Aron Henriksson are currently visiting the Division of Biomedical Informatics (DBMI) at the University of California, San Diego, which is located in the San Diego Supercomputer Center (SDSC). The visit will last for a month and is one of several exchanges between the Natural Language Processing (NLP) group at DBMI and the Clinical Text Mining Group at DSV that have been made possible through the Interlock project.
Last week we were invited together with Wendy Chapman to give a talk at a PACE (Predictive Analytics Center of Excellence) seminar at SDSC. Wendy first talked about NLP in general, while Maria and I talked about our respective research on NLP in the clinical domain.
-
- San Diego Supercomputer Center
-
- Maria talking about named entity recognition
-
- Aron talking about distributional semantics
-
- The NLP group eating out in La Jolla
Forum öppna data 6/12 2012: Stockholm EPR Open and DrugView
Martin Hassel and Alyaa Alfalahi presenting the Stockholm EPR Open project at Vinnova. The prototype DrugView where one can see in-patient groups and their intake of at least two medical drugs.
Coling 2012, Bombay, India, 9-14 December
The 24th International Conference on Computational Linguistics, Coling 2012 took place in Bombay (Mumbai) India, December 9-14. It is the largest computational linguistics conference in the world. At the conference were 600 participants from 60 countries. 1600 papers were submitted to the conference and 400 were accepted, that gives an acceptance rate of 25 percent.
Claudia Ehrentraut my master student from Uppsala University presented our paper: Detection of Hospital Acquired Infections in sparse and noisy Swedish patient records. A machine learning approach using Naïve Bayes, Support Vector Machines and C4.5, that was written by Claudia Ehrentraut, Hideyuki Tanushi, Hercules Dalianis and Jörg Tiedemann at the workshop Sixth Workshop on Analytics for Noisy Unstructured Text Data, AND 2012 that was held in conjunction with the conference.
We have written a short report from the conference, if you would like to have it please contact me.
