%0 Conference Paper %1 Bilke:2005:a %A Bilke, Alexander %A Bleiholder, Jens %A Böhm, Christoph %A Draba, Karsten %A Naumann, Felix %A Weis, Melanie %B Proc. of the 31st International Conference on Very Large Data Bases (VLDB), Demo Abstract Band %D 2005 %K imported %T Automatic data fusion with HumMer %U http://www.informatik.hu-berlin.de/mac/publications/VLDB2005.pdf %X Heterogeneous and dirty data is abundant. It is stored under different, often opaque schemata, it represents identical real-world objects multiple times, causing duplicates, and it has missing values and conflicting values. The Humboldt Merger (HumMer) is a tool that allows ad-hoc, declarative fusion of such data using a simple extension to SQL.Guided by a query against multiple tables, HumMer proceeds in three fully automated steps: First, instance-based schema matching bridges schematic heterogeneity of the tables by aligning corresponding attributes. Next, duplicate detection techniques find multiple representations of identical real-world objects. Finally, data fusion and conflict resolution merges duplicates into a single, consistent, and clean representation. %@ 1-59593-154-6

@inproceedings{Bilke:2005:a, abstract = {Heterogeneous and dirty data is abundant. It is stored under different, often opaque schemata, it represents identical real-world objects multiple times, causing duplicates, and it has missing values and conflicting values. The Humboldt Merger (HumMer) is a tool that allows ad-hoc, declarative fusion of such data using a simple extension to SQL.Guided by a query against multiple tables, HumMer proceeds in three fully automated steps: First, instance-based schema matching bridges schematic heterogeneity of the tables by aligning corresponding attributes. Next, duplicate detection techniques find multiple representations of identical real-world objects. Finally, data fusion and conflict resolution merges duplicates into a single, consistent, and clean representation.}, added-at = {2007-10-23T13:35:30.000+0200}, author = {Bilke, Alexander and Bleiholder, Jens and B\"ohm, Christoph and Draba, Karsten and Naumann, Felix and Weis, Melanie}, biburl = {https://www.bibsonomy.org/bibtex/288f318f8b0bfe4f942b1894f52307a4b/tkirsten}, booktitle = {Proc. of the 31st International Conference on Very Large Data Bases (VLDB), Demo Abstract Band}, interhash = {000cbc310ca4e9f3aeedc722988307fa}, intrahash = {88f318f8b0bfe4f942b1894f52307a4b}, isbn = {1-59593-154-6}, keywords = {imported}, location = {Trondheim, Norway}, owner = {kirsten}, timestamp = {2007-10-23T13:35:32.000+0200}, title = {{Automatic data fusion with HumMer}}, url = {http://www.informatik.hu-berlin.de/mac/publications/VLDB2005.pdf}, year = 2005 }