This paper describes a large-scale language-independent evaluation of the use of Thematic Hierarchies in natural language generation. We translate from a corpus of sentences reeecting the full variety of behavior of Levin-based verb classes. The corpus is used as input to a generation system that utilizes the same thematic hierarchy for realizing relative argument surface positions in two langu...

This paper describes a large-scale language-independent evaluation of the use of Thematic Hierarchies in natural language generation. We translate from a corpus of sentences reeecting the full variety of behavior of Levin-based verb classes. The corpus is used as input to a generation system that utilizes the same thematic hierarchy for realizing relative argument surface positions in two langu...

Geospatial semantics as a research field studies how to publish, retrieve, reuse, and integrate geo-data, how to describe geo-data by conceptual models, and how to develop formal specifications on top of data structures to reduce the risk of incompatibilities. Geo-data is highly heterogeneous and ranges from qualitative interviews and thematic maps to satellite imagery and complex simulations. ...

It is suggested that new ways of thinking about spatial analysis are required to optimize the use of digital tec hnologies. “Real-world-to-map” simplifications must be quantified and incorporated into spatial analysis with particular emphasis on boundary and category error. This could also lead to a better way to integrate thematic map-based and remotely-sensed data. However, such developments ...

conclusions the dimensions and variables affecting the surveyors’ management were identified and classified on the basis of existing scientific methods in the form of a conceptual framework. using the results of this study, it would certainly be possible to take a great step toward enhancing the reliability of surveys and the quality and safety of services, while effectively managing accreditat...

LetSum is a summarization system developed for producing short summaries for legal decisions. LetSum is built with an approach based on the exploration of the document structure and thematic segmentation in order to produce a table-style summary for improving coherency and readability of the text. We present the components of the system and its implementation.

Efficient tracking of class performance across topics is an important aspect of classroom teaching; this is especially true for psychometric general intelligence exams, which test a varied range of abilities. We develop a framework that uncovers a hidden thematic structure underlying student responses to a large pool of questions, using a probabilistic graphical model.

Introduction Simple recurrent networks (SRNs) are able to learn and represent lexical classes (Elman, 1990) and grammatical knowledge, such as agreement and argument structure (Elman, 1991), on the basis of co-occurrence regularities embedded in simple and complex sentences. In the present study, we address the question whether SRNs can represent differences in the thematic roles assigned by ve...

Topic modeling is an unsupervised machine-learning task of discovering topics, the underlying thematic structure in a text corpus. Dynamic topic models are capable of analysing the time evolution of topics. This paper explores the application of dynamic topic models on emergency department triage notes to identify particular types of disease or injury events, and to detect the temporal nature o...