|
Undoubtly, the availability of information for biomedicine in an electronic format has been rapidly increasing. The Medical Literature Analysis and Retrieval system (Medline) houses millions of biomedical scientific literature publications. PubMed offers the power of a search engine for accessing the Medline content. On the other hand, the electronization of clinical data within the Electronic Medical Record (EMR) provides another powerful source for information extraction. Access to integrated information is critical for health care improvement, research, and the overall science of healthcare delivery and personalized medicine. Information extraction from the scientific literature is distinct from information extraction from the clinical narrative as these two types of genre have their own stylistic characteristics and pose different methodological challenges. In addition, biomedical information spans multiple languages thus necessitating methods for multi-lingual information extraction.
In addition to the biomedical scientific literature and clinical data, we need also to consider the large number of health related web resources that is increasing day by day. The content of these resources is rather variable and difficult to assess. Furthermore, the number of people searching for health-related information is also increasing. The development of tools to support the process of describing the content of medical web resources with meta-data that facilitate their retrieval, and with quality labels by certified authorities, is crucial for the delivery of content of better quality to health information consumers. Multi-lingual information extraction has a significant role to play there also.
The focus of this workshop is natural language processing and information extraction for biomedicine, including scientific and clinical free-text as well as health-related web resources within one or many languages. Topics of interest include but are not limited to:
- Natural language processing techniques for basic tasks, e.g. sentence boundary detection, tokenization, part of speech tagging, shallow parsing and deep parsing. Evaluation and comparison with the general domain;
- Efforts to create sharable biomedical lexical resources, including the annotation of biomedical data for linguistic and domain events;
- Biomedical named entity recognition;
- Methods for higher level biomedical language processing, e.g. relation discovery, temporal relation discovery, anaphoric relation discovery;
- Terminology/ontology biomedical named entity mapping;
- Integrated knowledge management of scientific and clinical free-text data
- Knowledge representation and management technologies (e.g. OWL, RDF, Annotation Schemas, etc.) that enable the creation of machine-processable descriptions of health-related web resources
- Content collection and information extraction techniques that allow the quality labeling of web resources and the continuous monitoring of already labeled ones
- Multi-lingual information extraction.
 |
Important dates:
- Extended Submission deadline: 21 June 2009
- Notification of acceptance: 20 July 2009
- Camera-ready copy due from authors: 24 August 2009
- Workshop: 18 September 2009
Submission instructions:
Submissions should be A4, two-column format and should not exceed seven pages including cover page, figures, tables and references. The workshop papers should follow the RANLP format which is available at the RANLP website http://www.lml.bas.bg/ranlp2009 in the Second Call for Papers. Papers should be submitted electronically as *PDF* files using the conference submission system START. Detailed instructions about the workshop submission will be announced at the workshop website.
|
Review and multiple submission policy
The review process is anonymous. The paper text should not reveal the authors identity. To maintain the submissions, all authors' names and addresses should be registered in the START system when the paper is submitted; this information will be open for the workshop organizers only. Submissions will be reviewed by 3 members of the Programme Committee. Authors of accepted papers will receive guidelines regarding how to produce camera-ready versions of their papers for inclusion in the proceedings. The full workshop proceedings will be distributed at the event. The workshop papers will be included in the ACL Anthology.
The workshop calls for articles describing original research. Authors may submit the same paper at several events. In this case they must notify the organizers in a separate mail to [savova dot guergana at mayo dot edu], to inform them that the paper might be withdrawn depending on the selections at some other event.
Organizing committee:
Guergana Savova, Mayo Clinic College of Medicine, Rochester, Minnesota, USA
Vangelis Karkaletsis, Institute of Informatics and Telecommunications, Athens, Greece
Galia Angelova, Bulgarian Academy of Sciences, Sofia, Bulgaria
Programme committee
Werner Ceusters, Psychiatry and Ontology, SUNY at Buffalo
Wendy Chapman, Biomedical informatics, University of Pittsburgh
Cheryl Clark, MITRE Corporation
Kevin Cohen, University of Colorado
Noemie Elhadad, Biomedical Informatics, Columbia University
Udo Hahn, Jena University
Dimitris Kokkinakis, Gothenburg University
Stasinos Konstantopoulos, Institute of Informatics and Telecommunications, Athens
Anastassia Krithara, Institute of Informatics and Telecommunications, Athens
John Pestian, Biomedical Informatics, Cincinnati's Children's Hospital
Sunghwan Sohn, Biomedical statistics and informatics, Mayo Clinic
Vojtech Svatek, University of Economics, Prague
REVIEWERS
In addition to the members of the Programme Committee and the Organisers,
the following colleagues were involved in the reviewing process:
Svetla Boytcheva, State University of Library Studies
 and Information Technologies, Bulgaria
Georgi Georgiev, Ontotext AD, Bulgaria
Pythagoras Karampiperis, Institute of Informatics
and Telecommunications, Athens, Greece
Preslav Nakov, National University of Singapore, Singapore
Dimitar Tcharaktchiev, Medical University, Sofia, Bulgaria
|
Workshop venue:
The workshop will be held at the Samokov Hotel in the resort of Borovets as a post-conference event of RANLP-09. The picturesque resort of Borovets is located in the Rila mountains and is one of the best known winter resorts in South-East Europe, a frequent venue for world skiing events. The resort is 1350 m above sea level, at the foot of the highest peak on the Balkan Peninsula - Moussala (2925 m). The resort of Borovets is 73 km from Sofia and the International airport of Sofia can serve as an arrival/departure point. In addition to regular public transport, the organizers will provide daily shuttle buses from Sofia airport to the Samokov hotel at an inexpensive rate. A taxi from Sofia to Borovets is relatively cheap; it is also possible to take a taxi from the International airport in Sofia to the workshop venue.
Contact us at: [savova dot guergana at mayo dot edu]
|