Adaptive Blocking: Learning to Scale Up Record Linkage

By Mikhail Bilenko, Beena Kamath, Raymond J. Mooney. 2006

284 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Fast Learning from Distributed Datasets without Entity Matching (2016, methodology): “ER takesO(m(2)/H(2) · Tsim) to match entities in each of theH blocks, whereTsim is the cost of evaluation a similarity function; learning-b ased methods spend additional time for training; advanced blocking stra tegies can reduce the average complexity [4, 32, 31].”
Author Name Disambiguation in MEDLINE (2009, background): “, excluding pairwise comparisons that mismatch on middle initial for the most frequent names), or other possible speed-ups suggested for related computational problems such as adaptive blocking [Bilenko et al. 2006], sparse quadratic programming [Dominguez and Gonzalez-Lima 2006], approximate joins ”
Trends in Cleaning Relational Data: Consistency and Deduplication (2015, unknown): “different blocks are considered non-duplicates [4, 14].”
Entity resolution with iterative blocking (2009, methodology): “Various blocking techniques [19, 24, 5, 16, 13, 11, 15, 2, 10] have been proposed to make ER scalable.”
An Introduction to Duplicate Detection (2010, methodology): “1 BLOCKING Blocking methods pursue the simple idea of partitioning the set of records into disjoint partitions (blocks) and then comparing all pairs of records only within each block [Ananthakrishna et al., 2002; Baxter et al., 2003; Bilenko et al., 2006].”
Disambiguation and co-authorship networks of the U.S. patent inventor database (1975–2010) (2014, methodology): “, 2005; Bilenko et al., y 43 (2014) 941–955”
Learning similarity metrics for event identification in social media (2010, methodology): “Other solutions propose “blocking” methods [9, 20, 30], which partition elements into several subsets based on a rough measure of similarity, and then use traditional clustering algorithms (e.”
Data Matching (2012, methodology): “Two machine learning based approaches to define optimal blocking keys have recently been proposed [34, 188].”
Effective Data Cleaning with Continuous Evaluation (2016, methodology): “The scale challenge is often addressed using a variety of techniques including the use of sampling [17], approximate cleaning by partitioning the data into blocks as often done in data deduplication [3], and by adopting scale-out computing infrastructure such as Spark [19].”
Frameworks for entity matching: A comparison (2010, background): “The key may have to be determined manually or (semi-)automatically based on training data [10] [42].”
A Survey of Indexing Techniques for Scalable Record Linkage and Deduplication (2012, methodology): “Recently, two supervised machine learning-based approaches to optimally select blocking keys have been proposed [52], [53].”
LIMES - A Time-Efficient Approach for Large-Scale Link Discovery on the Web of Data (2011, methodology): “Different blocking techniques such as standard blocking, sorted-neighborhood, bigram indexing, canopy clustering and adaptive blocking [2, 5, 12] have been developed to address the problem of the quadratic time complexity of brute force comparison methods.”