In this research we compare two approaches (in particular, character-based machine learning and language modeling) and according to their results offer the best solution for the diacritization problem solving. Parameters of tested approaches (i.e., a huge variety of feature types for the character-based method and a value n for the n-gram language modeling method) were tuned to achieve the highest accuracy. Despite the main focus is on the Lithuanian language, we posit that obtained findings can also be applied to other, similar (Latvian or Slavic) languages. During experiments we measured the performance of used approaches on 10 domains (including normative texts and non-normative Internet comments). The best results reaching ~99.5% and ~98.4% of the accuracy on characters and words, respectively, were achieved with the tri-gram language modeling method. It outperformed the character-based machine learning approach with the tuned feature set by ~1.4% and ~3.8% of the accuracy on characters and words, respectively.

This paper presents a new approach how to reconstruct a parametric surface from a partially structured and noisy cloud of points representing surface that has a centre-line, such that all perpendicular rays to that line intersects with a surface not more than once. Presented algorithm analyses partially structured cloud of points, generated by point based 3D scanner and calculates parameters to build a non-uniform B-spline 3D mesh.