@inproceedings{bd0b8388ae7740d185094b20e3372cb1,
title = "Real-time entity resolution by multiple indices",
abstract = "Entity resolution (ER) is the process of extracting and matching records/tuples from one or more datasets that refer to the same real-world entity and merging the matching records into a tuple or a cluster. In this paper, we primarily focus on ER for datasets with text attributes. By creating different local indices on individual attributes and constructing the corresponding algorithm and ranking function for indices, we present an approach to resolve records involving duplicates, misspellings, or NULL text attributes for a dirty dataset. Extensive experiments are conducted to demonstrate the performances of our proposed approach.",
keywords = "Dirty dataset, Entity resolution, Multiple indices, Ranking function, Text attribute",
author = "Liang Zhu and Rundong Cui and Qin Ma and Weiyi Meng",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 14th International Conference on Computer Science and Education, ICCSE 2019 ; Conference date: 19-08-2019 Through 21-08-2019",
year = "2019",
month = aug,
doi = "10.1109/ICCSE.2019.8845358",
language = "English",
series = "14th International Conference on Computer Science and Education, ICCSE 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1063--1068",
booktitle = "14th International Conference on Computer Science and Education, ICCSE 2019",
}