Interactive deduplication using active learning

By Sunita Sarawagi, Anuradha Bhamidipaty. Knowledge Discovery and Data Mining, 2002

789 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/2174a2dc940e16896a2b016ad6b3635cbbbdec23

How researchers see this paper

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

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

A Survey of Indexing Techniques for Scalable Record Linkage and Deduplication (2012, background): “Many of them are based on machine learning approaches [10], [20], [28], [29], [30], [31].”
Large-Scale Deduplication with Constraints Using Dedupalog (2009, methodology): “There has also been work on learning similarity functions in an interactive fashion using active learning [38].”
Adaptive Blocking: Learning to Scale Up Record Linkage (2006, methodology): “For example, in record linkage (also known as object identification [35], de-duplication [31], entity matching [9, 33, 2] and identity uncertainty [29, 23]), similarity must be computed between all pairs of records to identify groups of records that refer to the same underlying entity.”
Trio: A System for Integrated Management of Data, Accuracy, and Lineage (2004, methodology): “Some approaches to data cleaning exploit lineage, e.g., [GFS+01], and deduplication is especially important when integrating data from multiple sources, e.g, [ SB02 ].”
Big Data: A Survey (2014, neutral): “copies [75].”
An interactive clustering-based approach to integrating source query interfaces on the deep Web (2004, methodology): “Interactive learning of classifiers is explored in [28] in the context of deduplication.”
A Latent Dirichlet Model for Unsupervised Entity Resolution (2005, methodology): “Beyond applying standard machine learning techniques, other approaches use active learning [32].”
Frameworks for entity matching: A comparison (2010, methodology): “[62] a Multiple Classifier System approach is proposed that employs a variety of supervised learners for combining matchers, including decision trees, 1-rule, Naïve Bayes, linear and logistic regression, back propagation neural network, and k-nearest neighbors.”
Data Matching (2012, methodology): “Such interactive approaches are known as active learning [11, 231, 252].”
Scaling Up Crowd-Sourcing to Very Large Datasets: A Case for Active Learning (2014, methodology): “We found several other entity resolution algorithms [3, 30] to be less eective than [4] and thus omit those from our comparisons here.”
Adaptive duplicate detection using learnable string similarity measures (2003, background): “Categories and Subject Descriptors H.2.8 [Database Management]: Database Applications -Data Mining; I.2.6 [Arti.cial Intelligence]: Learning Keywords Data cleaning, record linkage, distance metric learning, trained similarity measures, string edit distance, SVM applications 1.”
Distributed Representations of Tuples for Entity Resolution (2017, methodology): “Popular approaches include SVM [7], active learning [45], clustering [12].”
Principles of dataspace systems (2006, methodology): “Another example of this approach was taken in [48], where the system used an active learning method to carefully select questions that helped the system reconcile different references to the same real-world object.”
On the Ontology Instance Matching Problem (2008, background): “More generally, instance matching is frequently referred to as an Entity Resolution problem (also called Deduplication [2]) and it is defined as the process of identifying and merging records judged to represent the same real-world entity [3].”
Efficient exact set-similarity joins (2006, background): “A similarity join is an important operation for reconciling different representations of an entity [9, 11, 16, 21].”
Reference reconciliation in complex information spaces (2005, methodology): “as record linkage [37], merge/purge [21], de-duplication [34], hardening soft databases [9], reference matching [27], object identification [35] and identity uncertainty [26].”
Guided data repair (2011, background): “Similar grouping ideas have been explored in [19].”
Data integration: the teenage years (2006, background): “In some cases we can leverage work thats users are doing as a part of their job [32], in others we can solicit some help by asking some well chosen questions [79, 99, 106], and in others we simply exploit structure that already exists such as large numbers of schemas or web service descriptions [36,”