Osman Başkaya, Eray Yildiz, Doruk Tunaoğlu, Mustafa Tolga Eren, A. Seza Doğruöz. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

Agglutinative languages such as Turkish, Finnish andHungarian require morphological disambiguation beforefurther processing due to the complex morphologyof words. A morphological disambiguator is usedto select the correct morphological analysis of a word.Morphological disambiguation is important because itgenerally is one of the first steps of natural languageprocessing and its performance affects subsequent analyses.In this paper, we propose a system that uses deeplearning techniques for morphological disambiguation.Many of the state-of-the-art results in computer vision,speech recognition and natural language processinghave been obtained through deep learning models.However, applying deep learning techniques to morphologicallyrich languages is not well studied. In this work,while we focus on Turkish morphological disambiguationwe also present results for French and German inorder to show that the proposed architecture achieveshigh accuracy with no language-specific feature engineeringor additional resource. In the experiments, weachieve 84.12 , 88.35 and 93.78 morphological disambiguationaccuracy among the ambiguous words forTurkish, German and French respectively.

We propose a novel multi-view visualization technique, which allows effortless interaction with subterranean data and tries to maximize spatial perception whilst minimizing view clutter. The multi-view augmented reality technique introduces two correlating displays; i) a perspective egocentric view with focused edge overlay and focused geometry clipping and ii) an orthographic cut-away display that visualizes a thin slice of subterranean data intersecting a user controlled anchor.

Many professional tasks such as geographic or archaeological surveying require editing and processing spatial data. User generated models act as an underlying level for visualizing annotations. For accurate and fast placement of annotations in the field we introduce a mobile modelling workflow. Our contribution includes i) a novel annotation technique based on geometric regions and ii) a modelling workflow optimized for mobile devices.