Conference paper
Proceedings of the 12th International Conference on Natural Language Generation, Association for Computational Linguistics, Tokyo, Japan, 2019 Oct, pp. 504--507
Assistant Professor in Computer Science with focus on “Databases and Data Engineering”
APA
Click to copy
Niklaus, C., Cetto, M., Freitas, A., & Handschuh, S. (2019). DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German. In Proceedings of the 12th International Conference on Natural Language Generation (pp. 504–507). Tokyo, Japan: Association for Computational Linguistics.
Chicago/Turabian
Click to copy
Niklaus, Christina, Matthias Cetto, André Freitas, and Siegfried Handschuh. “DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German.” In Proceedings of the 12th International Conference on Natural Language Generation, 504–507. Tokyo, Japan: Association for Computational Linguistics, 2019.
MLA
Click to copy
Niklaus, Christina, et al. “DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German.” Proceedings of the 12th International Conference on Natural Language Generation, Association for Computational Linguistics, 2019, pp. 504–07.
BibTeX Click to copy
@inproceedings{niklaus2019a,
title = {DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German},
year = {2019},
month = oct,
address = {Tokyo, Japan},
pages = {504--507},
publisher = {Association for Computational Linguistics},
author = {Niklaus, Christina and Cetto, Matthias and Freitas, André and Handschuh, Siegfried},
booktitle = {Proceedings of the 12th International Conference on Natural Language Generation},
month_numeric = {10}
}
We introduce DisSim, a discourse-aware sentence splitting framework for English and German whose goal is to transform syntactically complex sentences into an intermediate representation that presents a simple and more regular structure which is easier to process for downstream semantic applications. For this purpose, we turn input sentences into a twolayered semantic hierarchy in the form of core facts and accompanying contexts, while identifying the rhetorical relations that hold between them. In that way, we preserve the coherence structure of the input and, hence, its interpretability for downstream tasks.