CLEF-ER 2013: Named Entity Recognition (NER) in parallel multilingual biomedical corpora (aiming for terminology translation)
26 March 2013 - 26 September 2013
Austria
OBJECTIVES
-- -- -- -- -- -- -- -- -- -- -- --
The workshop addresses the multilingual identification of mentions of named entities in corpora and the development of multilingual biomedical terminological resources. Relevant scientific questions are:
- Can we build multilingual biomedical terminologies from parallel
biomedical corpora?
- How do we exploit machine translation methods to identify
correspondences in parallel corpora?
- Do we encounter the same semantic representation in different languages?
- Can we make use of crowd-sourcing solutions to produce comprehensive
terminological resources?
The workshop is related but not limited to the CLEF-ER challenge (http://www.clefer.org(opens in new window)) where multilingual NER is performed using corpora in English, French, German, Spanish, and Dutch. Currently patent texts, titles of Medline abstracts and EMEA documents serve as parallel corpora, and mention annotations are explicitly referenced to entities, which are specified through a Concept Unique Identifier (CUI, from the UMLS).
TIME and PLACE
-- -- -- -- -- -- -- -- -- -- -- --
CLEF 2013 Conference, 23-26 September in Valencia, Spain.
We ask for contributions concerning the following topics:
* Scientific manuscripts in multilingual term recognition and machine
translation in the biomedical domain
* Perspective papers on multi-lingual term recognition in the
biomedical domain for their languages
* Perspective papers on the status and prospect of ML resource for
European languages in the biomedical domain, and the perspective for
non-European languages
* Machine-translation solutions for solving the multi-lingual term
recognition in the biomedical domain
[The best contribution wins a prize, which is the waiving of
publication costs in an open access journal]
TIMELINE
-- -- -- -- -- -- -- -- -- -- -- --
* 31-Mar : submission of abstracts, statements of intent
* 30-Apr : submission of the full paper manuscripts
* 31-May : review results
* 15-Jun: submission of the final paper to the CLEF organisers
ORGANIZERS
-- -- -- -- -- -- -- -- -- -- -- --
* D. Rebholz-Schuhmann, F. Rinaldi, S. Clematide, Institute of
Computational Linguistics, Universität Zürich (Ch)
* Prof. U. Hahn, J. Hellrich, Julie Laboratory, Universität Jena (D)
* J. Kors, E. van Mulligen, Erasmus University Medical Center, Rotterdam (Nl)
* D. Milward, I. Lewin, Linguamatics Ltd, Cambridge (UK)
* P. Daumke, M. Poprat, Averbis GmbH, Freiburg (D)
* J. McEntyre, S. Kafkas, EMBL-EBI, Hinxton, Cambridge, U.K.
-- -- -- -- -- -- -- -- -- -- -- --
The workshop addresses the multilingual identification of mentions of named entities in corpora and the development of multilingual biomedical terminological resources. Relevant scientific questions are:
- Can we build multilingual biomedical terminologies from parallel
biomedical corpora?
- How do we exploit machine translation methods to identify
correspondences in parallel corpora?
- Do we encounter the same semantic representation in different languages?
- Can we make use of crowd-sourcing solutions to produce comprehensive
terminological resources?
The workshop is related but not limited to the CLEF-ER challenge (http://www.clefer.org(opens in new window)) where multilingual NER is performed using corpora in English, French, German, Spanish, and Dutch. Currently patent texts, titles of Medline abstracts and EMEA documents serve as parallel corpora, and mention annotations are explicitly referenced to entities, which are specified through a Concept Unique Identifier (CUI, from the UMLS).
TIME and PLACE
-- -- -- -- -- -- -- -- -- -- -- --
CLEF 2013 Conference, 23-26 September in Valencia, Spain.
We ask for contributions concerning the following topics:
* Scientific manuscripts in multilingual term recognition and machine
translation in the biomedical domain
* Perspective papers on multi-lingual term recognition in the
biomedical domain for their languages
* Perspective papers on the status and prospect of ML resource for
European languages in the biomedical domain, and the perspective for
non-European languages
* Machine-translation solutions for solving the multi-lingual term
recognition in the biomedical domain
[The best contribution wins a prize, which is the waiving of
publication costs in an open access journal]
TIMELINE
-- -- -- -- -- -- -- -- -- -- -- --
* 31-Mar : submission of abstracts, statements of intent
* 30-Apr : submission of the full paper manuscripts
* 31-May : review results
* 15-Jun: submission of the final paper to the CLEF organisers
ORGANIZERS
-- -- -- -- -- -- -- -- -- -- -- --
* D. Rebholz-Schuhmann, F. Rinaldi, S. Clematide, Institute of
Computational Linguistics, Universität Zürich (Ch)
* Prof. U. Hahn, J. Hellrich, Julie Laboratory, Universität Jena (D)
* J. Kors, E. van Mulligen, Erasmus University Medical Center, Rotterdam (Nl)
* D. Milward, I. Lewin, Linguamatics Ltd, Cambridge (UK)
* P. Daumke, M. Poprat, Averbis GmbH, Freiburg (D)
* J. McEntyre, S. Kafkas, EMBL-EBI, Hinxton, Cambridge, U.K.