@inbook{224e39261e0f43208db73aa2281ecb0a,
title = "Parsing a markup language that supports overlap and discontinuity",
abstract = "Text As Graph Markup Language (TAGML) is a recently developed markup language that offers core support for overlapping and discontinuous markup. Designing and implementing a markup language technology stack that supports overlap poses numerous challenges; the most prominent being that the markup language cannot be expressed in a recursive context-free (CF) grammar. In this short paper we discuss our experiments with parsing TAGML based on a context-sensitive grammar. Our current approach implements an attribute grammar, which consists of a CF grammar with semantic actions. We discuss the advantages and disadvantages of our approach, and sketch several alternative methods.",
keywords = "Attribute grammar, Context sensitive grammar, Hyperedge replacement grammar, Markup language, Overlap, Parser combinator library, Parser generator, Parsing, Parsing with derivations",
author = "Dekker, {Ronald Haentjens} and Bram Buitendijk and Elli Bleeker",
note = "Publisher Copyright: {\textcopyright} 2020 ACM.",
year = "2020",
month = sep,
day = "29",
doi = "10.1145/3395027.3419590",
language = "English",
series = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2020",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2020",
}