@inproceedings{36dc26843c394fac9f5dcd2412fa9ff0,
title = "Inferring a relax NG schema from XML documents",
abstract = "An XML schema specifies the structural properties of XML documents generated from the schema and, thus, is useful to manage XML data efficiently. However, there are often XML documents without a valid schema or with an incorrect schema in practice. This leads us to study the problem of inferring a Relax NG schema from a set of XML documents that are presumably generated from a specific XML schema. Relax NG is an XML schema language developed for the next generation of XML schema languages such as document type definitions (DTDs) and XML Schema Definitions (XSDs). Regular hedge grammars accept regular tree languages and the design of Relax NG is closely related with regular hedge grammars. We develop an XML schema inference system using hedge grammars. We employ a genetic algorithm and state elimination heuristics in the process of retrieving a concise Relax NG schema. We present experimental results using real-world benchmark.",
keywords = "Genetic algorithm, Regular hedge grammar, Relax NG, XML schema inference",
author = "Kim, {Guen Hae} and Ko, {Sang Ki} and Han, {Yo Sub}",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 10th International Conference on Language and Automata Theory and Applications, LATA 2016 ; Conference date: 14-03-2016 Through 18-03-2016",
year = "2016",
doi = "10.1007/978-3-319-30000-9_31",
language = "English",
isbn = "9783319299990",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "400--411",
editor = "Bianca Truthe and Jan Janou{\v s}ek and Adrian-Horia Dediu and Carlos Mart{\'i}n-Vide",
booktitle = "Language and Automata Theory and Applications - 10th International Conference, LATA 2016, Proceedings",
address = "Germany",
}