Michael Dorna

Electronics, software and sensor systems have become key technologies in agriculture. Future development steps are autonomous field robots with high technological challenges and options for economical and ecological benefits. The robustness of autonomous robots is considered to be of highest relevance for a step from present research activities towards prototypes. The application ‘crop scout’ has been identified as a promising option to realise such a robot, called BoniRob, in an interdisciplinary cooperation with partners from electronic and agricultural industry as well as research institutions from engineering and agriculture. The vehicle is based on four wheel hub motors and hydraulic components, thereby offering a high flexibility with respect to navigation and changing height positions. Multi-sensor fusion - including complex sensor systems like spectral imaging and 3D time-of-flight cameras – and a RTK-DGPS system are applied for an individual plant phenotyping. The navigation concept of BoniRob is based on probabilistic robotics. A Gazebo-based 3D simulation environment for BoniRob is developed, including options for data and software exchange between the simulator and the real robot. In the first stage maize and wheat are considered for phenotyping, sensor and plant parameters have been defined according to the extended BBCH scale. As an additional option mapping of plant diseases based on spectral imaging information will be evaluated. The automatic phenotyping and mapping of all plants in a field will be a revolutionary change in the methods of field trials. Moreover, the availability of a robust crops scout platform will offer options for other field applications.

This article presents a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer formalism together with its procedural realization. Our approach is discussed and compared with several other approaches from the MT literature. The results presented in this article have been implemented and integrated into the Verbmobil system.

In this paper we present an ambiguity preserving translation approach which transfers ambiguous LFG f-structure representatios. It is based on packed f-structure representations which are the result of potentially ambiguous utterances. If the ambiguities between source and target language can be preserved, no unpacking during transfer is necessary and the generator may produce utterances which maximally cover the underlying ambiguities. We convert the packed f-structure descriptions into a flat set of prolog terms which consist of predicates, their predicate argument structure and additional attribute-value information. Ambiguity is expressed via local disjunctions. The flat representations facilitate the application of a Shake-and-Bake like transfer approach extended to deal with packed ambiguites.

While automatic term extraction is a wellresearched area, computational approaches to distinguish between degrees of technicality are still understudied. We semi-automatically create a German gold standard of technicality across four domains, and illustrate the impact of a web-crawled general-language corpus on predicting technicality. When defining a classification approach that combines general-language and domain-specific word embeddings, we go beyond previous work and align vector spaces to gain comparative embeddings. We suggest two novel models to exploit general-vs. domain-specific comparisons: a simple neural network model with pre-computed comparative-embedding information as input, and a multi-channel model computing the comparison internally. Both models outperform previous approaches, with the multi-channel model performing best.