@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{SchirmerPapenbrockKoumarelasetal.2020, author = {Schirmer, Philipp and Papenbrock, Thorsten and Koumarelas, Ioannis and Naumann, Felix}, title = {Efficient discovery of matching dependencies}, series = {ACM transactions on database systems : TODS}, volume = {45}, journal = {ACM transactions on database systems : TODS}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0362-5915}, doi = {10.1145/3392778}, pages = {33}, year = {2020}, abstract = {Matching dependencies (MDs) are data profiling results that are often used for data integration, data cleaning, and entity matching. They are a generalization of functional dependencies (FDs) matching similar rather than same elements. As their discovery is very difficult, existing profiling algorithms find either only small subsets of all MDs or their scope is limited to only small datasets. We focus on the efficient discovery of all interesting MDs in real-world datasets. For this purpose, we propose HyMD, a novel MD discovery algorithm that finds all minimal, non-trivial MDs within given similarity boundaries. The algorithm extracts the exact similarity thresholds for the individual MDs from the data instead of using predefined similarity thresholds. For this reason, it is the first approach to solve the MD discovery problem in an exact and truly complete way. If needed, the algorithm can, however, enforce certain properties on the reported MDs, such as disjointness and minimum support, to focus the discovery on such results that are actually required by downstream use cases. HyMD is technically a hybrid approach that combines the two most popular dependency discovery strategies in related work: lattice traversal and inference from record pairs. Despite the additional effort of finding exact similarity thresholds for all MD candidates, the algorithm is still able to efficiently process large datasets, e.g., datasets larger than 3 GB.}, language = {en} } @book{Naumann2008, author = {Naumann, Felix}, title = {Informationsqualit{\"a}t : Antrittsvorlesung 2007-04-26}, publisher = {Univ.-Bibl.}, address = {Potsdam}, year = {2008}, abstract = {Sowohl in kommerziellen als auch in wissenschaftlichen Datenbanken sind Daten von niedriger Qualit{\"a}t allgegenw{\"a}rtig. Das kann zu erheblichen wirtschaftlichen Problemen f{\"u}hren", erl{\"a}utert der 35-j{\"a}hrige Informatik-Professor und verweist zum Beispiel auf Duplikate. Diese k{\"o}nnen entstehen, wenn in Unternehmen verschiedene Kundendatenbest{\"a}nde zusammengef{\"u}gt werden, aber die Integration mehrere Datens{\"a}tze des gleichen Kunden hinterl{\"a}sst. "Solche doppelten Eintr{\"a}ge zu finden, ist aus zwei Gr{\"u}nden schwierig: Zum einen ist die Menge der Daten oft sehr groß, zum anderen k{\"o}nnen sich Eintr{\"a}ge {\"u}ber die gleiche Person leicht unterscheiden", beschreibt Prof. Naumann h{\"a}ufig auftretende Probleme. In seiner Antrittsvorlesung will er zwei L{\"o}sungswege vorstellen: Erstens die Definition geeigneter {\"A}hnlichkeitsmaße und zweitens die Nutzung von Algorithmen, die es vermeiden, jeden Datensatz mit jedem anderen zu vergleichen. Außerdem soll es um grundlegende Aspekte der Verst{\"a}ndlichkeit, Objektivit{\"a}t, Vollst{\"a}ndigkeit und Fehlerhaftigkeit von Daten gehen.}, language = {de} } @article{MomtaziNaumann2013, author = {Momtazi, Saeedeh and Naumann, Felix}, title = {Topic modeling for expert finding using latent Dirichlet allocation}, series = {Wiley interdisciplinary reviews : Data mining and knowledge discovery}, volume = {3}, journal = {Wiley interdisciplinary reviews : Data mining and knowledge discovery}, number = {5}, publisher = {Wiley}, address = {San Fransisco}, issn = {1942-4787}, doi = {10.1002/widm.1102}, pages = {346 -- 353}, year = {2013}, abstract = {The task of expert finding is to rank the experts in the search space given a field of expertise as an input query. In this paper, we propose a topic modeling approach for this task. The proposed model uses latent Dirichlet allocation (LDA) to induce probabilistic topics. In the first step of our algorithm, the main topics of a document collection are extracted using LDA. The extracted topics present the connection between expert candidates and user queries. In the second step, the topics are used as a bridge to find the probability of selecting each candidate for a given query. The candidates are then ranked based on these probabilities. The experimental results on the Text REtrieval Conference (TREC) Enterprise track for 2005 and 2006 show that the proposed topic-based approach outperforms the state-of-the-art profile- and document-based models, which use information retrieval methods to rank experts. Moreover, we present the superiority of the proposed topic-based approach to the improved document-based expert finding systems, which consider additional information such as local context, candidate prior, and query expansion.}, language = {en} } @book{MeinelPlattnerDoellneretal.2014, author = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick}, title = {Proceedings of the 7th Ph.D. Retreat of the HPI Research School on Service-oriented Systems Engineering}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-273-5}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63490}, publisher = {Universit{\"a}t Potsdam}, pages = {ii, 218}, year = {2014}, abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the Research Scholl, this technical report covers a wide range of research topics. These include but are not limited to: Self-Adaptive Service-Oriented Systems, Operating System Support for Service-Oriented Systems, Architecture and Modeling of Service-Oriented Systems, Adaptive Process Management, Services Composition and Workflow Planning, Security Engineering of Service-Based IT Systems, Quantitative Analysis and Optimization of Service-Oriented Systems, Service-Oriented Systems in 3D Computer Graphics sowie Service-Oriented Geoinformatics.}, language = {en} } @book{MeinelDoellnerWeskeetal.2021, author = {Meinel, Christoph and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick and Friedrich, Tobias and B{\"o}ttinger, Erwin and Lippert, Christoph and D{\"o}rr, Christian and Lehmann, Anja and Renard, Bernhard and Rabl, Tilmann and Uebernickel, Falk and Arnrich, Bert and H{\"o}lzle, Katharina}, title = {Proceedings of the HPI Research School on Service-oriented Systems Engineering 2020 Fall Retreat}, number = {138}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-513-2}, issn = {1613-5652}, doi = {10.25932/publishup-50413}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-504132}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 144}, year = {2021}, abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the research school, this technical report covers a wide range of topics. These include but are not limited to: Human Computer Interaction and Computer Vision as Service; Service-oriented Geovisualization Systems; Algorithm Engineering for Service-oriented Systems; Modeling and Verification of Self-adaptive Service-oriented Systems; Tools and Methods for Software Engineering in Service-oriented Systems; Security Engineering of Service-based IT Systems; Service-oriented Information Systems; Evolutionary Transition of Enterprise Applications to Service Orientation; Operating System Abstractions for Service-oriented Computing; and Services Specification, Composition, and Enactment.}, language = {en} } @misc{LosterNaumannEhmuelleretal.2018, author = {Loster, Michael and Naumann, Felix and Ehmueller, Jan and Feldmann, Benjamin}, title = {CurEx}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3269229}, pages = {1883 -- 1886}, year = {2018}, abstract = {The integration of diverse structured and unstructured information sources into a unified, domain-specific knowledge base is an important task in many areas. A well-maintained knowledge base enables data analysis in complex scenarios, such as risk analysis in the financial sector or investigating large data leaks, such as the Paradise or Panama papers. Both the creation of such knowledge bases, as well as their continuous maintenance and curation involves many complex tasks and considerable manual effort. With CurEx, we present a modular system that allows structured and unstructured data sources to be integrated into a domain-specific knowledge base. In particular, we (i) enable the incremental improvement of each individual integration component; (ii) enable the selective generation of multiple knowledge graphs from the information contained in the knowledge base; and (iii) provide two distinct user interfaces tailored to the needs of data engineers and end-users respectively. The former has curation capabilities and controls the integration process, whereas the latter focuses on the exploration of the generated knowledge graph.}, 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.
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} } @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} } @misc{KruseKaoudiQuianeRuizetal.2019, author = {Kruse, Sebastian and Kaoudi, Zoi and Quiane-Ruiz, Jorge-Arnulfo and Chawla, Sanjay and Naumann, Felix and Contreras-Rojas, Bertty}, title = {Optimizing Cross-Platform Data Movement}, series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)}, journal = {2019 IEEE 35th International Conference on Data Engineering (ICDE)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7474-1}, issn = {1084-4627}, doi = {10.1109/ICDE.2019.00162}, pages = {1642 -- 1645}, year = {2019}, abstract = {Data analytics are moving beyond the limits of a single data processing platform. A cross-platform query optimizer is necessary to enable applications to run their tasks over multiple platforms efficiently and in a platform-agnostic manner. For the optimizer to be effective, it must consider data movement costs across different data processing platforms. In this paper, we present the graph-based data movement strategy used by RHEEM, our open-source cross-platform system. In particular, we (i) model the data movement problem as a new graph problem, which we prove to be NP-hard, and (ii) propose a novel graph exploration algorithm, which allows RHEEM to discover multiple hidden opportunities for cross-platform data processing.}, language = {en} }