@inproceedings{57f002ee189b405a959216997a9ba7f4,
title = "Fast phonetic similarity search over large repositories",
abstract = "Analysis of unstructured data may be inefficient in the presence of spelling errors. Existing approaches use string similarity methods to search for valid words within a text, with a supporting dictionary. However, they are not rich enough to encode phonetic information to assist the search. In this paper, we present a novel approach for efficiently perform phonetic similarity search over large data sources, that uses a data structure called PhoneticMap to encode language-specific phonetic information. We validate our approach through an experiment over a data set using a Portuguese variant of a well-known repository, to automatically correct words with spelling errors.",
keywords = "Fast Search, Phonetic Similarity, String Similarity",
author = "Hegler Tissot and Gabriel Peschl and {Del Fabro}, {Marcos Didonet}",
year = "2014",
doi = "10.1007/978-3-319-10085-2_6",
language = "English",
isbn = "9783319100845",
series = "Lecture Notes in Computer Science",
publisher = "Springer, Springer Nature",
pages = "74--81",
editor = "Hendrik Decker and Lenka Lhotsk{\'a} and Sebastian Link and Marcus Spies and Wagner, {Roland R.}",
booktitle = "Database and Expert Systems Applications",
address = "United States",
note = "25th International Conference on Database and Expert Systems Applications, DEXA 2014 ; Conference date: 01-09-2014 Through 04-09-2014",
}