Ralf Klabunde


2023

pdf
Validating Predictive Models Of Evaluative Language For Controllable Data2Text Generation
Maurice Langner | Ralf Klabunde
Proceedings of the 16th International Natural Language Generation Conference

In data2text generation, tabular data is transformed into a text that expresses information from that source domain. While some text types, such as instructions, demand objective and neutral language without any expressive and evaluative content, many other text types are expected to provide expressions for these kinds of subjective meanings. In controllable, pipelined neural NLG separate learning models, notably regression models, can be used to predict whether some feature deviates sufficiently strongly from an expected value, so that evaluative language would be appropriate for verbalizing this finding. In this paper, we present an empirical study on the comprehension of evaluative adverbs and adjectival modifiers in car reviews, a text type that is characterized by a mixture of factual information with evaluations expressing positive or negative surprise. We show to what extend regression-based decision boundaries for producing evaluative content in controllable data2text NLG match the reader’s expectations that are raised by those evaluative markers. Finally we show that regression values in combination with standard deviation of the technical input data constitute reasonable Boolean thresholds for both positive and negative surprise, which provide the basis for the development of more complex models that also include the scalar base of adverbs and modifiers.

2022

pdf
Testing Focus and Non-at-issue Frameworks with a Question-under-Discussion-Annotated Corpus
Christoph Hesse | Maurice Langner | Ralf Klabunde | Anton Benz
Proceedings of the Thirteenth Language Resources and Evaluation Conference

We present an annotated corpus of German driving reports for the analysis of Question-under-Discussion (QUD) based information structural distinctions. Since QUDs can hardly be defined in advance for providing a corresponding tagset, several theoretical issues arise concerning the scope and quality of the corpus and the development of an appropriate annotation tool for creating the corpus. We developed the corpus for testing the adequacy of QUD-based pragmatic frameworks of information structure. First analyses of the annotated information structures show that focus-related meaning aspects are essentially confirmed, indicating a sufficent accuracy of the annotations. Assumptions on non-at-issueness expressed by non-restrictive relative clauses made in the literature seem to be too strong, given the corpus data.

2020

pdf bib
Proceedings of the Workshop on Discourse Theories for Text Planning
Christoph Hesse | Maurice Langner | Anton Benz | Ralf Klabunde
Proceedings of the Workshop on Discourse Theories for Text Planning

pdf
Annotating QUDs for generating pragmatically rich texts
Christoph Hesse | Anton Benz | Maurice Langner | Felix Theodor | Ralf Klabunde
Proceedings of the Workshop on Discourse Theories for Text Planning

2015

pdf
A Strategic Reasoning Model for Generating Alternative Answers
Jon Stevens | Anton Benz | Sebastian Reuße | Ralf Klabunde
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2013

pdf
Greetings Generation in Video Role Playing Games
Björn Schlünder | Ralf Klabunde
Proceedings of the 14th European Workshop on Natural Language Generation

2009

pdf
Towards a Game-Theoretic Approach to Content Determination
Ralf Klabunde
Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009)

2007

pdf
Lexical choice of modal expressions
Ralf Klabunde
Proceedings of the Eleventh European Workshop on Natural Language Generation (ENLG 07)

2005

pdf
When must Should Be Chosen
Ralf Klabunde
Proceedings of the Tenth European Workshop on Natural Language Generation (ENLG-05)

2000

pdf
Planning word-order dependant focus assignments
Cornelia Endriss | Ralf Klabunde
INLG’2000 Proceedings of the First International Conference on Natural Language Generation

1998

pdf
Abductive Reasoning for Syntactic Realization
Ralf Klabunde | Martin Jansche
Natural Language Generation