@phdthesis{Bauckmann2013,
  author    = {Bauckmann, Jana},
  title     = {Dependency discovery for data integration},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66645},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Data integration aims to combine data of different sources and to provide users with a unified view on these data. This task is as challenging as valuable. In this thesis we propose algorithms for dependency discovery to provide necessary information for data integration. We focus on inclusion dependencies (INDs) in general and a special form named conditional inclusion dependencies (CINDs): (i) INDs enable the discovery of structure in a given schema. (ii) INDs and CINDs support the discovery of cross-references or links between schemas. An IND "A in B" simply states that all values of attribute A are included in the set of values of attribute B. We propose an algorithm that discovers all inclusion dependencies in a relational data source. The challenge of this task is the complexity of testing all attribute pairs and further of comparing all of each attribute pair's values. The complexity of existing approaches depends on the number of attribute pairs, while ours depends only on the number of attributes. Thus, our algorithm enables to profile entirely unknown data sources with large schemas by discovering all INDs. Further, we provide an approach to extract foreign keys from the identified INDs. We extend our IND discovery algorithm to also find three special types of INDs: (i) Composite INDs, such as "AB in CD", (ii) approximate INDs that allow a certain amount of values of A to be not included in B, and (iii) prefix and suffix INDs that represent special cross-references between schemas. Conditional inclusion dependencies are inclusion dependencies with a limited scope defined by conditions over several attributes. Only the matching part of the instance must adhere the dependency. We generalize the definition of CINDs distinguishing covering and completeness conditions and define quality measures for conditions. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. The challenge for this task is twofold: (i) Which (and how many) attributes should be used for the conditions? (ii) Which attribute values should be chosen for the conditions? Previous approaches rely on pre-selected condition attributes or can only discover conditions applying to quality thresholds of 100\%. Our approaches were motivated by two application domains: data integration in the life sciences and link discovery for linked open data. We show the efficiency and the benefits of our approaches for use cases in these domains.},
  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}
}