@article{VitaglianoHameedJiangetal.2023,
  author    = {Vitagliano, Gerardo and Hameed, Mazhar and Jiang, Lan and Reisener, Lucas and Wu, Eugene and Naumann, Felix},
  title     = {Pollock: a data loading benchmark},
  series = {Proceedings of the VLDB Endowment},
  volume    = {16},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {8},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3594512.3594518},
  pages     = {1870 -- 1882},
  year      = {2023},
  abstract  = {Any system at play in a data-driven project has a fundamental requirement: the ability to load data. The de-facto standard format to distribute and consume raw data is CSV. Yet, the plain text and flexible nature of this format make such files often difficult to parse and correctly load their content, requiring cumbersome data preparation steps. We propose a benchmark to assess the robustness of systems in loading data from non-standard CSV formats and with structural inconsistencies. First, we formalize a model to describe the issues that affect real-world files and use it to derive a systematic lpollutionz process to generate dialects for any given grammar. Our benchmark leverages the pollution framework for the csv format. To guide pollution, we have surveyed thousands of real-world, publicly available csv files, recording the problems we encountered. We demonstrate the applicability of our benchmark by testing and scoring 16 different systems: popular csv parsing frameworks, relational database tools, spreadsheet systems, and a data visualization tool.},
  language  = {en}
}
@article{BonifatiMiorNaumannetal.2022,
  author    = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina},
  title     = {How inclusive are we?},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {50},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3516431.3516438},
  pages     = {30 -- 35},
  year      = {2022},
  abstract  = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors. <br /> We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.},
  language  = {en}
}
@article{SimoniniZecchiniBergamaschietal.2022,
  author    = {Simonini, Giovanni and Zecchini, Luca and Bergamaschi, Sonia and Naumann, Felix},
  title     = {Entity resolution on-demand},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {7},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3523210.3523226},
  pages     = {1506 -- 1518},
  year      = {2022},
  abstract  = {Entity Resolution (ER) aims to identify and merge records that refer to the same real-world entity. ER is typically employed as an expensive cleaning step on the entire data before consuming it. Yet, determining which entities are useful once cleaned depends solely on the user's application, which may need only a fraction of them. For instance, when dealing with Web data, we would like to be able to filter the entities of interest gathered from multiple sources without cleaning the entire, continuously-growing data. Similarly, when querying data lakes, we want to transform data on-demand and return the results in a timely manner-a fundamental requirement of ELT (Extract-Load-Transform) pipelines. We propose BrewER, a framework to evaluate SQL SP queries on dirty data while progressively returning results as if they were issued on cleaned data. BrewER tries to focus the cleaning effort on one entity at a time, following an ORDER BY predicate. Thus, it inherently supports top-k and stop-and-resume execution. For a wide range of applications, a significant amount of resources can be saved. We exhaustively evaluate and show the efficacy of BrewER on four real-world datasets.},
  language  = {en}
}
@article{GrafLaskowskiPapsdorfetal.2022,
  author    = {Graf, Martin and Laskowski, Lukas and Papsdorf, Florian and Sold, Florian and Gremmelspacher, Roland and Naumann, Felix and Panse, Fabian},
  title     = {Frost: a platform for benchmarking and exploring data matching results},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {12},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3554821.3554823},
  pages     = {3292 -- 3305},
  year      = {2022},
  abstract  = {"Bad" data has a direct impact on 88\% of companies, with the average company losing 12\% of its revenue due to it. Duplicates - multiple but different representations of the same real-world entities are among the main reasons for poor data quality, so finding and configuring the right deduplication solution is essential. Existing data matching benchmarks focus on the quality of matching results and neglect other important factors, such as business requirements. Additionally, they often do not support the exploration of data matching results. To address this gap between the mere counting of record pairs vs. a comprehensive means to evaluate data matching solutions, we present the Frost platform. It combines existing benchmarks, established quality metrics, cost and effort metrics, and exploration techniques, making it the first platform to allow systematic exploration to understand matching results. Frost is implemented and published in the open-source application Snowman, which includes the visual exploration of matching results, as shown in Figure 1.},
  language  = {en}
}
@article{HackerNaumannFriedrichetal.2022,
  author    = {Hacker, Philipp and Naumann, Felix and Friedrich, Tobias and Grundmann, Stefan and Lehmann, Anja and Zech, Herbert},
  title     = {AI compliance - challenges of bridging data science and law},
  series = {Journal of Data and Information Quality (JDIQ)},
  volume    = {14},
  journal   = {Journal of Data and Information Quality (JDIQ)},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3531532},
  pages     = {4},
  year      = {2022},
  abstract  = {This vision article outlines the main building blocks of what we term AI Compliance, an effort to bridge two complementary research areas: computer science and the law. Such research has the goal to model, measure, and affect the quality of AI artifacts, such as data, models, and applications, to then facilitate adherence to legal standards.},
  language  = {en}
}
@article{CaruccioDeufemiaNaumannetal.2021,
  author    = {Caruccio, Loredana and Deufemia, Vincenzo and Naumann, Felix and Polese, Giuseppe},
  title     = {Discovering relaxed functional dependencies based on multi-attribute dominance},
  series = {IEEE transactions on knowledge and data engineering},
  volume    = {33},
  journal   = {IEEE transactions on knowledge and data engineering},
  number    = {9},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {New York, NY},
  issn      = {1041-4347},
  doi       = {10.1109/TKDE.2020.2967722},
  pages     = {3212 -- 3228},
  year      = {2021},
  abstract  = {With the advent of big data and data lakes, data are often integrated from multiple sources. Such integrated data are often of poor quality, due to inconsistencies, errors, and so forth. One way to check the quality of data is to infer functional dependencies (fds). However, in many modern applications it might be necessary to extract properties and relationships that are not captured through fds, due to the necessity to admit exceptions, or to consider similarity rather than equality of data values. Relaxed fds (rfds) have been introduced to meet these needs, but their discovery from data adds further complexity to an already complex problem, also due to the necessity of specifying similarity and validity thresholds. We propose Domino, a new discovery algorithm for rfds that exploits the concept of dominance in order to derive similarity thresholds of attribute values while inferring rfds. An experimental evaluation on real datasets demonstrates the discovery performance and the effectiveness of the proposed algorithm.},
  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{VitaglianoJiangNaumann2021,
  author    = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix},
  title     = {Detecting layout templates in complex multiregion files},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3494124.3494145},
  pages     = {646 -- 658},
  year      = {2021},
  abstract  = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.},
  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}
}
@article{BonnetDongNaumannetal.2021,
  author    = {Bonnet, Philippe and Dong, Xin Luna and Naumann, Felix and T{\"o}z{\"u}n, P{\i}nar},
  title     = {VLDB 2021},
  series = {SIGMOD record},
  volume    = {50},
  journal   = {SIGMOD record},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3516431.3516447},
  pages     = {50 -- 53},
  year      = {2021},
  abstract  = {The 47th International Conference on Very Large Databases (VLDB'21) was held on August 16-20, 2021 as a hybrid conference. It attracted 180 in-person attendees in Copenhagen and 840 remote attendees. In this paper, we describe our key decisions as general chairs and program committee chairs and share the lessons we learned.},
  language  = {en}
}