@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} } @phdthesis{Koumarelas2020, author = {Koumarelas, Ioannis}, title = {Data preparation and domain-agnostic duplicate detection}, doi = {10.25932/publishup-48913}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489131}, school = {Universit{\"a}t Potsdam}, pages = {x, 97}, year = {2020}, abstract = {Successfully completing any data science project demands careful consideration across its whole process. Although the focus is often put on later phases of the process, in practice, experts spend more time in earlier phases, preparing data, to make them consistent with the systems' requirements or to improve their models' accuracies. Duplicate detection is typically applied during the data cleaning phase, which is dedicated to removing data inconsistencies and improving the overall quality and usability of data. While data cleaning involves a plethora of approaches to perform specific operations, such as schema alignment and data normalization, the task of detecting and removing duplicate records is particularly challenging. Duplicates arise when multiple records representing the same entities exist in a database. Due to numerous reasons, spanning from simple typographical errors to different schemas and formats of integrated databases. Keeping a database free of duplicates is crucial for most use-cases, as their existence causes false negatives and false positives when matching queries against it. These two data quality issues have negative implications for tasks, such as hotel booking, where users may erroneously select a wrong hotel, or parcel delivery, where a parcel can get delivered to the wrong address. Identifying the variety of possible data issues to eliminate duplicates demands sophisticated approaches. While research in duplicate detection is well-established and covers different aspects of both efficiency and effectiveness, our work in this thesis focuses on the latter. We propose novel approaches to improve data quality before duplicate detection takes place and apply the latter in datasets even when prior labeling is not available. Our experiments show that improving data quality upfront can increase duplicate classification results by up to 19\%. To this end, we propose two novel pipelines that select and apply generic as well as address-specific data preparation steps with the purpose of maximizing the success of duplicate detection. Generic data preparation, such as the removal of special characters, can be applied to any relation with alphanumeric attributes. When applied, data preparation steps are selected only for attributes where there are positive effects on pair similarities, which indirectly affect classification, or on classification directly. Our work on addresses is twofold; first, we consider more domain-specific approaches to improve the quality of values, and, second, we experiment with known and modified versions of similarity measures to select the most appropriate per address attribute, e.g., city or country. To facilitate duplicate detection in applications where gold standard annotations are not available and obtaining them is not possible or too expensive, we propose MDedup. MDedup is a novel, rule-based, and fully automatic duplicate detection approach that is based on matching dependencies. These dependencies can be used to detect duplicates and can be discovered using state-of-the-art algorithms efficiently and without any prior labeling. MDedup uses two pipelines to first train on datasets with known labels, learning to identify useful matching dependencies, and then be applied on unseen datasets, regardless of any existing gold standard. Finally, our work is accompanied by open source code to enable repeatability of our research results and application of our approaches to other datasets.}, language = {en} } @article{DraisbachChristenNaumann2019, author = {Draisbach, Uwe and Christen, Peter and Naumann, Felix}, title = {Transforming pairwise duplicates to entity clusters for high-quality duplicate detection}, series = {ACM Journal of Data and Information Quality}, volume = {12}, journal = {ACM Journal of Data and Information Quality}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3352591}, pages = {1 -- 30}, year = {2019}, abstract = {Duplicate detection algorithms produce clusters of database records, each cluster representing a single real-world entity. As most of these algorithms use pairwise comparisons, the resulting (transitive) clusters can be inconsistent: Not all records within a cluster are sufficiently similar to be classified as duplicate. Thus, one of many subsequent clustering algorithms can further improve the result.
We explain in detail, compare, and evaluate many of these algorithms and introduce three new clustering algorithms in the specific context of duplicate detection. Two of our three new algorithms use the structure of the input graph to create consistent clusters. Our third algorithm, and many other clustering algorithms, focus on the edge weights, instead. For evaluation, in contrast to related work, we experiment on true real-world datasets, and in addition examine in great detail various pair-selection strategies used in practice. While no overall winner emerges, we are able to identify best approaches for different situations. In scenarios with larger clusters, our proposed algorithm, Extended Maximum Clique Clustering (EMCC), and Markov Clustering show the best results. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.}, language = {en} }