PhD Position in Linguistics/Computer Science in Jena, Germany

Employer
Friedrich Schiller University Jena
Location
Germany
Posted
July 03 2017
Discipline
Other
Position Type
Full Time
Organization Type
Academia

The Collaborative Research Center SFB 1076 “AquaDiva - Understanding the Links between Surface and Subsurface Biogeosphere” is funded by the Deutsche Forschungsgemeinschaft (DFG). AquaDiva is an ambitious research center with more than 70 researchers and Institutes at four faculties of the Friedrich Schiller University Jena (FSU) and three non-university research institutes in Jena or Leipzig. The integrated Research Training Group AquaDiva is educating doctoral researchers in a structured, interdisciplinary training program. AquaDiva combines different research areas, such as ecology, microbiology, hydrogeology, soil science, geochemistry, geology, geophysics, chemistry, and information science, to a comprehensive picture of subsurface research (www.aquadiva.uni-jena.de).


The Integrated Research Training Group AquaDiva invites applications for a


Doctoral Researcher Position (m/f; Ref.No. 152/2017)


at the Jena University Language and Information Engineering (JULIE) Lab,


Friedrich Schiller University Jena (FSU)


Semantic Technologies for Scientific Data Management and Text Mining (SemDaTe)


The SemDaTe project provides the information management and sharing platform for the whole of the CRC AquaDiva. Within this framework, JULIE Lab is responsible for semantic text analytics of unstructured scientific documents (journal articles, technical reports, etc.). The doctoral researcher's task is to provide support at three levels of text-based data management. First, data integration, i.e. the closer coupling between data held in structured databases and unstructured textual data available in verbal publications; second, data interpretation, i.e. whether the data are credible (trust models of data), consistent (detection of conflicting data), and complete (detection of missing data); and third, data abstraction by semantic generalization of single data items (model or theory discovery, i.e. “real” text mining complemented by text summarization).


Major tasks:



  • Maintain and enhance an existing software framework - SeMedico, a semantic search engine, and, in collaboration with the Distributed Information System Group, enhancement of the common BExIS data portal




  • Work on the three main topics for this funding period: data integration, data interpretation, and data abstraction from the perspective of semantic text analytics





This job comes from a partnership with Science Magazine and Euraxess