@incollection{LuengenBaerenfaengerHilbertetal.2016, author = {Harald L{\"u}ngen and Maja B{\"a}renf{\"a}nger and Mirco Hilbert and Henning Lobin and Csilla Pusk{\´a}s}, title = {Discourse Relations and Document Structure}, series = {Linguistic Modeling of Information and Markup Languages. Contributions to Language Technology}, editor = {Andreas Witt and Metzing Dieter}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-90-481-3330-7}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-48005}, pages = {97 -- 123}, year = {2016}, abstract = {This chapter addresses the requirements and linguistic foundations of automatic relational discourse analysis of complex text types such as scientific journal articles. It is argued that besides lexical and grammatical discourse markers, which have traditionally been employed in discourse parsing, cues derived from the logical and generical document structure and the thematic structure of a text must be taken into account. An approach to modelling such types of linguistic information in terms of XML-based multi-layer annotations and to a text-technological representation of additional knowledge sources is presented. By means of quantitative and qualitative corpus analyses, cues and constraints for automatic discourse analysis can be derived. Furthermore, the proposed representations are used as the input sources for discourse parsing. A short overview of the projected parsing architecture is given.}, language = {en} }