@article{KoumarelasJiangNaumann2020,
  author    = {Koumarelas, Ioannis and Jiang, Lan and Naumann, Felix},
  title     = {Data preparation for duplicate detection},
  series = {Journal of data and information quality : (JDIQ)},
  volume    = {12},
  journal   = {Journal of data and information quality : (JDIQ)},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3377878},
  pages     = {24},
  year      = {2020},
  abstract  = {Data errors represent a major issue in most application workflows. Before any important task can take place, a certain data quality has to be guaranteed by eliminating a number of different errors that may appear in data. Typically, most of these errors are fixed with data preparation methods, such as whitespace removal. However, the particular error of duplicate records, where multiple records refer to the same entity, is usually eliminated independently with specialized techniques. Our work is the first to bring these two areas together by applying data preparation operations under a systematic approach prior to performing duplicate detection. <br /> Our process workflow can be summarized as follows: It begins with the user providing as input a sample of the gold standard, the actual dataset, and optionally some constraints to domain-specific data preparations, such as address normalization. The preparation selection operates in two consecutive phases. First, to vastly reduce the search space of ineffective data preparations, decisions are made based on the improvement or worsening of pair similarities. Second, using the remaining data preparations an iterative leave-one-out classification process removes preparations one by one and determines the redundant preparations based on the achieved area under the precision-recall curve (AUC-PR). Using this workflow, we manage to improve the results of duplicate detection up to 19\% in AUC-PR.},
  language  = {en}
}
@book{DraisbachNaumannSzottetal.2012,
  author    = {Draisbach, Uwe and Naumann, Felix and Szott, Sascha and Wonneberg, Oliver},
  title     = {Adaptive windows for duplicate detection},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-143-1},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53007},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {41},
  year      = {2012},
  abstract  = {Duplicate detection is the task of identifying all groups of records within a data set that represent the same real-world entity, respectively. This task is difficult, because (i) representations might differ slightly, so some similarity measure must be defined to compare pairs of records and (ii) data sets might have a high volume making a pair-wise comparison of all records infeasible. To tackle the second problem, many algorithms have been suggested that partition the data set and compare all record pairs only within each partition. One well-known such approach is the Sorted Neighborhood Method (SNM), which sorts the data according to some key and then advances a window over the data comparing only records that appear within the same window. We propose several variations of SNM that have in common a varying window size and advancement. The general intuition of such adaptive windows is that there might be regions of high similarity suggesting a larger window size and regions of lower similarity suggesting a smaller window size. We propose and thoroughly evaluate several adaption strategies, some of which are provably better than the original SNM in terms of efficiency (same results with fewer comparisons).},
  language  = {en}
}
@article{HackerKrestelGrundmannetal.2020,
  author    = {Hacker, Philipp and Krestel, Ralf and Grundmann, Stefan and Naumann, Felix},
  title     = {Explainable AI under contract and tort law},
  series = {Artificial intelligence and law},
  volume    = {28},
  journal   = {Artificial intelligence and law},
  number    = {4},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0924-8463},
  doi       = {10.1007/s10506-020-09260-6},
  pages     = {415 -- 439},
  year      = {2020},
  abstract  = {This paper shows that the law, in subtle ways, may set hitherto unrecognized incentives for the adoption of explainable machine learning applications. In doing so, we make two novel contributions. First, on the legal side, we show that to avoid liability, professional actors, such as doctors and managers, may soon be legally compelled to use explainable ML models. We argue that the importance of explainability reaches far beyond data protection law, and crucially influences questions of contractual and tort liability for the use of ML models. To this effect, we conduct two legal case studies, in medical and corporate merger applications of ML. As a second contribution, we discuss the (legally required) trade-off between accuracy and explainability and demonstrate the effect in a technical case study in the context of spam classification.},
  language  = {en}
}
@book{AlbrechtNaumann2012,
  author    = {Albrecht, Alexander and Naumann, Felix},
  title     = {Understanding cryptic schemata in large extract-transform-load systems},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-201-8},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {19},
  year      = {2012},
  abstract  = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.},
  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}
}
@book{HerschelNaumann2008,
  author    = {Herschel, Melanie and Naumann, Felix},
  title     = {Space and time scalability of duplicate detection in graph data},
  isbn      = {978-3-940793-46-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32851},
  publisher      = {Universit{\"a}t Potsdam},
  year      = {2008},
  abstract  = {Duplicate detection consists in determining different representations of real-world objects in a database. Recent research has considered the use of relationships among object representations to improve duplicate detection. In the general case where relationships form a graph, research has mainly focused on duplicate detection quality/effectiveness. Scalability has been neglected so far, even though it is crucial for large real-world duplicate detection tasks. In this paper we scale up duplicate detection in graph data (DDG) to large amounts of data and pairwise comparisons, using the support of a relational database system. To this end, we first generalize the process of DDG. We then present how to scale algorithms for DDG in space (amount of data processed with limited main memory) and in time. Finally, we explore how complex similarity computation can be performed efficiently. Experiments on data an order of magnitude larger than data considered so far in DDG clearly show that our methods scale to large amounts of data not residing in main memory.},
  language  = {en}
}
@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}
}
@article{KossmannPapenbrockNaumann2021,
  author    = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix},
  title     = {Data dependencies for query optimization},
  series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
  volume    = {31},
  journal   = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
  number    = {1},
  publisher = {Springer},
  address   = {Berlin ; Heidelberg ; New York},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-021-00676-3},
  pages     = {1 -- 22},
  year      = {2021},
  abstract  = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.},
  language  = {en}
}
@article{LosterKoumarelasNaumann2021,
  author    = {Loster, Michael and Koumarelas, Ioannis and Naumann, Felix},
  title     = {Knowledge transfer for entity resolution with siamese neural networks},
  series = {ACM journal of data and information quality},
  volume    = {13},
  journal   = {ACM journal of data and information quality},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3410157},
  pages     = {25},
  year      = {2021},
  abstract  = {The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity-duplicates-into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise. <br /> We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.},
  language  = {en}
}