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.

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.

In recent years, referring expression genera- tion algorithms were inspired by game theory and probability theory. In this paper, an al- gorithm is designed for the generation of re- ferring expressions (REG) that base on both models by integrating maximization of utilities into the content determination process. It im- plements cognitive models for assessing visual salience of objects and additional features. In order to evaluate the algorithm properly and validate the applicability of existing models and evaluative information criteria, both, pro- duction and comprehension studies, are con- ducted using a complex domain of objects, pro- viding new directions of approaching the eval- uation of REG algorithms.

In recent years, Bayesian models of referring expression generation have gained prominence in order to produce situationally more adequate referring expressions. Basically, these models enable the integration of different parameters into the decision process for using a specific referring expression like the cardinality of the object set, the configuration and complexity of the visual field, and the discriminatory power of available attributes that need to be combined with visual salience and personal preference. This paper describes and discusses the results of an empirical study on the production of referring expressions in visual fields with different object configurations of varying complexity and different contextual premises for using a referring expression. The visual fields are set up using data from the TUNA experiment with plain random or pragmatically enriched configurations which allow for target inference. Different categories of the situational contexts, in which the referring expressions are produced, provide different degrees of cooperativeness, so that generation quality and its relations to contextual user intention can be observed. The results of the study suggest that Bayesian approaches must integrate individual generation preference and the cooperativeness of the situational task in order to model the broad variance between speakers more adequately.