@book{LangeBoehmNaumann2010,
  author    = {Lange, Dustin and B{\"o}hm, Christoph and Naumann, Felix},
  title     = {Extracting structured information from Wikipedia articles to populate infoboxes},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-081-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-45714},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {27},
  year      = {2010},
  abstract  = {Roughly every third Wikipedia article contains an infobox - a table that displays important facts about the subject in attribute-value form. The schema of an infobox, i.e., the attributes that can be expressed for a concept, is defined by an infobox template. Often, authors do not specify all template attributes, resulting in incomplete infoboxes. With iPopulator, we introduce a system that automatically populates infoboxes of Wikipedia articles by extracting attribute values from the article's text. In contrast to prior work, iPopulator detects and exploits the structure of attribute values for independently extracting value parts. We have tested iPopulator on the entire set of infobox templates and provide a detailed analysis of its effectiveness. For instance, we achieve an average extraction precision of 91\% for 1,727 distinct infobox template attributes.},
  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}
}