Object Matching (Entity resolution) is a critical data integration task and aims at identifying semantically corresponding objects (records, instances) in one or several data sources. A typical example is the redundant and heterogeneous representation of customers in different enterprise databases. Finding corresponding customer representations is a key task, e.g., for customer relationship management or master data management, in general. On the web, finding matching ovjects is typically even more challenging due to the higher degrees of heterogenity (less structured data with many text attributes, more sources, more data quality problems etc.).

MOMA, STEM, FEVER

We are developing comprehensive prototypes for object matching since 2006. A key idea is to support the combination of several match techniques (matchers) to improve the overall effectiveness in terms of precision and recall. The first prototype MOMA supports the construction of flexible workflows for object matching and the reuse of previous match results which are represented as instance mappings. Furthermore, MOMA not only uses the similarity of attribute values but also incorporates a powerful context matcher called neighborhood matcher.

The more recent frameworks STEM and FEVER support blocking and matching as well as the use of machine learning techniques. The machine learning approaches utilize a limited amount of training data (manually labeled correspondences) to semi-automatically find effective combinations of matchers. FEVER also supports the comparative evaluation of different match approaches for a given match task.

Specific entity resolution approaches have been developed to categorize and match product offers and product descriptions of web shops.

Benchmarking existing entity resolution approaches

In a VLDB 2010 paper we have used FEVER to comparatively evaluate existing entity resolution implementations. The datasets used in the evaluation can be downloaded here.

Please see also our recent work on cloud-based entity resolution and load balancing.

Project Members

• Prof. Dr. Erhard Rahm
• Hanna Köpcke
• Dr. Andreas Thor

Publications

Kolb, L.; Thor, A.; Rahm, E. Don't Match Twice: Redundancy-free Similarity Computation with MapReduce Proc. 2nd Intl. Workshop on Data Analytics in the Cloud (DanaC), 2013 2013-06

Ngonga Ngomo A.-C.; Kolb, L.; Heino, N.; Hartung, M.; Auer, S.; Rahm, E. When to Reach for the Cloud: Using Parallel Hardware for Link Discovery Proc. 10th Intl. Extended Semantic Web Conference (ESWC), 2013 2013-05

Kolb, L.; Rahm, E. Parallel Entity Resolution with Dedoop Datenbank-Spektrum 13 (1), 2013 2013-02-23

Kolb, L.; Thor, A.; Rahm, E. Dedoop: Efficient Deduplication with Hadoop Proc. 38th Intl. Conference on Very Large Databases (VLDB) / Proc. of the VLDB Endowment 5(12), 2012 2012-08

Kolb, L.; Thor, A.; Rahm, E. Load Balancing for MapReduce-based Entity Resolution Proc. 28th Intl. Conference on Data Engineering (ICDE), 2012 2012-04

Köpcke, H.; Thor, A.; Thomas, S.; Rahm, E. Tailoring entity resolution for matching product offers Proc. 15th Intl. Conf. on Extending Database Technology (EDBT), 2012, pp. 545-550 2012-03

Kolb, L.; Thor, A.; Rahm, E. Multi-pass Sorted Neighborhood Blocking with MapReduce Computer Science - Research and Development 27(1), 2012 2012-02

Kolb, L.; Köpcke, H.; Thor, A.; Rahm, E. Learning-based Entity Resolution with MapReduce Proc. 3rd Intl. Workshop on Cloud Data Management (CloudDB), 2011 2011-10

Kolb, L; Thor, A.; Rahm, E. Block-based Load Balancing for Entity Resolution with MapReduce Proc. 20th Intl. Conference on Information and Knowledge Management (CIKM), 2011 2011-10

Kolb, L.; Thor, A.; Rahm, E. Parallel Sorted Neighborhood Blocking with MapReduce Proc. 14th GI-Fachtagung für Datenbanksysteme in Business, Technologie und Web (BTW), 2011 2011-03

Köpcke, H.; Thor, A.; Rahm, E. Evaluation of entity resolution approaches on real-world match problems Proc. 36th Intl. Conference on Very Large Databases (VLDB) / Proceedings of the VLDB Endowment 3(1), 2010 2010-09

Kirsten, T.; Kolb, L.; Hartung, M.; Groß, A.; Köpcke, H.; Rahm, E. Data Partitioning for Parallel Entity Matching Proc. 8th Intl. Workshop on Quality in Databases (QDB), 2010 2010-09

Thor, A. Toward an adaptive String Similarity Measure for Matching Product Offers Proc. GI-Workshop - Informationsintegration in Service-Architekturen, 2010 2010-09

Köpcke, H.; Thor, A.; Rahm, E. Learning-based approaches for matching web data entities IEEE Internet Computing 14(4), 2010 2010-07

Köpcke, H.; Rahm, E. Frameworks for entity matching: A comparison Data & Knowledge Engineering 2010-01

Köpcke, H.; Thor, A.; Rahm, E. Comparative evaluation of entity resolution approaches with FEVER Proc. 35th Intl. Conference on Very Large Databases (VLDB), 2009 (demo) 2009-08

Köpcke, H.; Rahm, E. Training Selection for Tuning Entity Matching 6th International Workshop on Quality in Databases and Management of Uncertain Data (QDB/MUD 2008) 2008-08

Thor, A.; Kirsten, T.; Rahm, E. Instance-based matching of hierarchical ontologies Proc. of 12. GI-Fachtagung für Datenbanksysteme in Business, Technologie und Web (BTW), 2007 2007-03

Köpcke, H.; Rahm, E. Analyse von Zitierungshäufigkeiten für die Datenbankkonferenz BTW Datenbank-Spektrum, 7. Jahrgang, Heft 20 2007-02

Thor, A.; Rahm, E. MOMA - A Mapping-based Object Matching System Proc. 3rd Conference on Innovative Data Systems Research (CIDR), 2007 2007-01