MEDA 2018 – Workshop on Curative Power of MEdical DAta Workshop Proposal at JCDL2018 Daniela Gîfu
Diana Trandabăț
Alexandru Ioan Cuza University of Iasi & Romanian Academy, Iasi Branch, Romania
[email protected]
Alexandru Ioan Cuza University of Iasi Romania
[email protected]
Kevin Bretonnel Cohen
Jingbo Xia
Computational Bioscience Program U. Colorado School of Medicine
[email protected]
Huazhong Agricultural University P.R. China
[email protected]
•
1
OVERVIEW
In an era when massive amounts of medical data became available, researchers working in biological, biomedical and clinical domains have increasingly started to require the help of language engineers to process large quantities of biomedical and molecular biology literature (such as PubMed), patient data or health records. Linking the contents of these documents to each other, as well as to specialized ontologies, could enable access to and discovery of structured clinical information and foster a major leap in natural language processing and health research. MEDA-2018 aims to gather innovative approaches for the exploitation of biomedical data using semantic web technologies and linked data by bringing together practitioners, researchers, and scholars to share examples, use cases, theories and analysis of biomedical data. The main objective of this second edition workshop is to consolidate an internationally appreciated forum for scientific research in BioMed, with emphasis on crowdsourcing, semantic web, knowledge integration and data linking.
2
TOPICS
The scientific program of MEDA-2018 will focus around the following topics: • Crowdsourcing approaches in biomedicine • Collaborative computational technologies for biomedical research • Biomedical digital libraries • Mining biomedical literature • Event-based text mining for biology and related fields • Event and entity extraction in medical texts • Conceptual graphs extracted from medical texts
• • • • • • • •
3
Annotation of semantic content, with applications in medicine and biology Techniques for Big Data in Healthcare Medical search engines Distributed communication system in biomedical applications Deep learning for bioinformatics Biomedical question/answering Biomedical topic modeling Biomedical language systems Text summarization in the biomedical domain.
PROSPECTIVE PROGRAM COMMITTEE • • • • • • • • • • •
Gilles Adda (LIMSI-CNRS, Orsay, France) Yannis Almirantis (National Center for Scientific Research Demokritos, Athens, Greece) Anita Burgun (Université Paris Descartes, CPSC, France) Kevin Cohen (U. Colorado School of Medicine, United States & Université Paris-Saclay, Orsay, France) Trevor Cohen (University of Texas Health Science Center at Houston, School of Biomedical Informatics) Edward A Fox (Virginia Tech, Blacksburg, VA, United States) Eric Gaussier (Université Paris-Saclay, Orsay, France) Daniela Gîfu ("Alexandru Ioan Cuza" University of Iași, Romania & Romanian Academy – Iasi branch) Kishaloy Halder (School of Computing. National University of Singapore) Zhiyong Lu (National Center for Biotechnology Information, Bethesda, Maryland, US) Aurélie Névéol (LIMSI, CNRS, Université Paris-Saclay, Orsay, France)
MEDA-2018 Workshop Proposal • • • •
4
Diana Trandabăț ("Alexandru Ioan Cuza" University of Iași, Romania) Alfonso Valencia (CNIO, Spain) Jingbo Xia (Huazhong Agricultural University, P.R. China) Pierre Zweigenbaum (LIMSI, CNRS, Université ParisSaclay, Orsay, France)
AUDIENCE
The workshop will bring together practitioners, researchers, and scholars, especially on BioNLP and MedNLP issues, to share examples, use cases, theories, and analysis of biomedical and linked data, in order to address the intersection among these areas. This intersection includes not only the challenges of problems such as the understanding and acting upon large-scale data of different kinds, provenance, and reliability, but also the use of these media for data management, which involves issues of credibility, accountability, trustworthiness, privacy, authenticity, and provision of provenance information.
5
PAPER SELECTION
All papers will be reviewed by at least 2 members of the Program Committee. All reviews will be double blind, and hence authors are instructed not to include their identity, affiliation(s) or contact details, and to anonymize any references that would reveal the authorship of the paper. Papers submitted to other conferences or journals must state this fact. If a paper will appear in another conference or journal, it must be withdrawn from MEDA. We estimate having about 20-25 submitted papers at MEDA2018. The estimated paper acceptance rate will be around 6075%, in order to end up with about 15 accepted papers. The estimated number of participants of the conference is about 25, including presenters of accepted papers, researchers interested in discussions and accompanying persons.
6
FORMAT
The workshop is intended to be a half-day workshop, with presentation of accepted full papers, a short poster session and a final round table.
7
PREVIOUS EDITIONS
MEDA Workshop series has been initiated in 2017. The first edition took place in Romania, conjoint with EUROLAN 2017 Summer School. MEDA-2017 had 11 accepted papers and an acceptance rate of 52%. MEDA-2017 Proceedings was issued by the publishing house of Alexandru Ioan Cuza University of Iasi.
8
ORGANIZERS
Dr. Daniela Gifu is a scientific researcher at the Institute of Computer Science, Romanian Academy, Iasi Branch. The main areas of interest arising from her published scientific papers (more than 100) include: Web of Linked Data, Content Analysis, Semantic Annotation and Virtual Civic Identity. With two PhDs, 2
Daniela Gîfu, Diana Trandabăț, Kevin Cohen, Jingbo Xia one on political communication and one in computer science, she is an expert on Natural Language Processing issues at the Romanian Unit for Financing Higher Education, Research, Development and Innovation. Contact e-mail:
[email protected] Dr. Diana Trandabat is Associate Professor at the Faculty of Computer Science, University “Alexandru loan Cuza” of Iasi, Romania. The main focus of her research is natural language semantics and its application in different areas of language technologies, with emphasis on semantic media and sentiment identification, in the context of linked open data. With more than 70 research papers, an essential scientific achievement was the authored study of the current situation of LT for Romanian language. The 89 pages study Romanian Language in the digital age was published by Springer as part of the META-NET WhitePaper series, which analyzes the available language resources and technologies for 30 European languages. The analysis was carried out by META-NET, a Network of Excellence funded by the European Commission, of which she is a member. Contact email:
[email protected] Dr. Kevin Cohen is the Director of the Biomedical Text Mining Group at the University of Colorado, School of Medicine, and the D’Alembert Chair in Natural Language Processing for the Biomedical Domain at the Université Paris-Saclay (OR ParisSaclay University). His book Biomedical natural language processing, written with Dina Demner-Fushman, is the standard text on the subject. Kevin’s work covers both theoretical topics, such as lexical semantics, and practical applications, such as predicting pediatric epilepsy surgery candidates. Contact e-mail:
[email protected] Dr. Jingbo Xia is an associate professor in the Department of Big Data Science, College of Informatics, Huazhong Agricultural University, China, member of the Bioinformatics Key Laboratory of Hubei Province, and of the SIGBIOMED. He currently acted as an editorial team member of Journal of Mathematics research, and registered reviewer for Mathematical Reviews®, Bentham science publisher, Journal of Theoretical Biology, Journal of Math (Chinese edition), and Journal of Mathematics Research. He has a mathematics PhD, and he carried on research in data mining, bioinformatics and biomedical natural language processing. 20 of the 52 research papers published until 2017 are very high quality SCI indexed papers. Contact e-mail:
[email protected]