@article{NevesLeser2015,
  author    = {Neves, Mariana and Leser, Ulf},
  title     = {Question answering for Biology},
  series = {Methods : focusing on rapidly developing techniques},
  volume    = {74},
  journal   = {Methods : focusing on rapidly developing techniques},
  publisher = {Elsevier},
  address   = {San Diego},
  issn      = {1046-2023},
  doi       = {10.1016/j.ymeth.2014.10.023},
  pages     = {36 -- 46},
  year      = {2015},
  abstract  = {Biologists often pose queries to search engines and biological databases to obtain answers related to ongoing experiments. This is known to be a time consuming, and sometimes frustrating, task in which more than one query is posed and many databases are consulted to come to possible answers for a single fact. Question answering comes as an alternative to this process by allowing queries to be posed as questions, by integrating various resources of different nature and by returning an exact answer to the user. We have surveyed the current solutions on question answering for Biology, present an overview on the methods which are usually employed and give insights on how to boost performance of systems in this domain. (C) 2014 Elsevier Inc. All rights reserved.},
  language  = {en}
}
@article{ChiarcosDipperGoetzeetal.2008,
  author    = {Chiarcos, Christian and Dipper, Stefanie and G{\"o}tze, Michael and Leser, Ulf and L{\"u}deling, Anke and Ritz, Julia and Stede, Manfred},
  title     = {A flexible framework for integrating annotations from different tools and tag sets},
  issn      = {1248-9433},
  year      = {2008},
  abstract  = {We present a general framework for integrating annotations from different tools and tag sets. When annotating corpora at multiple linguistic levels, annotators may use different expert tools for different phenomena or types of annotation. These tools employ different data models and accompanying approaches to visualization, and they produce different output formats. For the purposes of uniformly processing these outputs, we developed a pivot format called PAULA, along with converters to and from tool formats. Different annotations are not only integrated at the level of data format, but are also joined on the level of conceptual representation. For this purpose, we introduce OLiA, an ontology of linguistic annotations that mediates between alternative tag sets that cover the same class of linguistic phenomena. All components are integrated in the linguistic information system ANNIS : Annotation tool output is converted to the pivot format PAULA and read into a database where the data can be visualized, queried, and evaluated across multiple layers. For cross-tag set querying and statistical evaluation, ANNIS uses the ontology of linguistic annotations. Finally, ANNIS is also tied to a machine learning component for semiautomatic annotation.},
  language  = {en}
}
@book{BauckmannLeserNaumann2010,
  author    = {Bauckmann, Jana and Leser, Ulf and Naumann, Felix},
  title     = {Efficient and exact computation of inclusion dependencies for data integration},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-048-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41396},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {36},
  year      = {2010},
  abstract  = {Data obtained from foreign data sources often come with only superficial structural information, such as relation names and attribute names. Other types of metadata that are important for effective integration and meaningful querying of such data sets are missing. In particular, relationships among attributes, such as foreign keys, are crucial metadata for understanding the structure of an unknown database. The discovery of such relationships is difficult, because in principle for each pair of attributes in the database each pair of data values must be compared. A precondition for a foreign key is an inclusion dependency (IND) between the key and the foreign key attributes. We present with Spider an algorithm that efficiently finds all INDs in a given relational database. It leverages the sorting facilities of DBMS but performs the actual comparisons outside of the database to save computation. Spider analyzes very large databases up to an order of magnitude faster than previous approaches. We also evaluate in detail the effectiveness of several heuristics to reduce the number of necessary comparisons. Furthermore, we generalize Spider to find composite INDs covering multiple attributes, and partial INDs, which are true INDs for all but a certain number of values. This last type is particularly relevant when integrating dirty data as is often the case in the life sciences domain - our driving motivation.},
  language  = {en}
}
@book{BauckmannAbedjanLeseretal.2012,
  author    = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix},
  title     = {Covering or complete? : Discovering conditional inclusion dependencies},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-212-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {34},
  year      = {2012},
  abstract  = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.},
  language  = {en}
}