Viera Rozinajová

Miroslav Blšták, Viera Rozinajová

Automatic question generation is one of the most challenging tasks of Natural Language Processing. It requires "bidirectional" language processing: firstly, the system has to understand the input text (Natural Language Understanding) and it then has to generate questions also in the form of text (Natural Language Generation). In this article, we introduce our framework for generating the factual questions from unstructured text in the English language. It uses a combination of traditional linguistic approaches based on sentence patterns with several machine learning methods. We firstly obtain lexical, syntactic and semantic information from an input text and we then construct a hierarchical set of patterns for each sentence. The set of features is extracted from the patterns and it is then used for automated learning of new transformation rules. Our learning process is totally data-driven because the transformation rules are obtained from a set of initial sentence-question pairs. The advantages of this approach lie in a simple expansion of new transformation rules which allows us to generate various types of questions and also in the continuous improvement of the system by reinforcement learning. The framework also includes a question evaluation module which estimates the quality of generated questions. It serves as a filter for selecting the best questions and eliminating incorrect ones or duplicates. We have performed several experiments to evaluate the correctness of generated questions and we have also compared our system with several state-of-the-art systems. Our results indicate that the quality of generated questions outperforms the state-of-the-art systems and our questions are also comparable to questions created by humans. We have also created and published an interface with all created datasets and evaluated questions, so it is possible to follow up on our work.

Peter Pavlík, Marc Schleiss, Anna Bou Ezzeddine et al.

Precipitation nowcasting -- the short-term prediction of rainfall using recent radar observations -- is critical for weather-sensitive sectors such as transportation, agriculture, and disaster mitigation. While recent deep learning models have shown promise in improving nowcasting skill, most approaches rely solely on 2D radar reflectivity fields, discarding valuable vertical information available in the full 3D radar volume. In this work, we explore the use of Echo Top Height (ETH), a 2D projection indicating the maximum altitude of radar reflectivity above a given threshold, as an auxiliary input variable for deep learning-based nowcasting. We examine the relationship between ETH and radar reflectivity, confirming its relevance for predicting rainfall intensity. We implement a single-pass 3D U-Net that processes both the radar reflectivity and ETH as separate input channels. While our models are able to leverage ETH to improve skill at low rain-rate thresholds, results are inconsistent at higher intensities and the models with ETH systematically underestimate precipitation intensity. Three case studies are used to illustrate how ETH can help in some cases, but also confuse the models and increase the error variance. Nonetheless, the study serves as a foundation for critically assessing the potential contribution of additional variables to nowcasting performance.

Peter Pavlík, Martin Výboh, Anna Bou Ezzeddine et al.

This paper presents a convolutional neural network model for precipitation nowcasting that combines data-driven learning with physics-informed domain knowledge. We propose LUPIN, a Lagrangian Double U-Net for Physics-Informed Nowcasting, that draws from existing extrapolation-based nowcasting methods. It consists of a U-Net that dynamically produces mesoscale advection motion fields, a differentiable semi-Lagrangian extrapolation operator, and an advection-free U-Net capturing the growth and decay of precipitation over time. Using our approach, we successfully implement the Lagrangian convolutional neural network for precipitation nowcasting in a fully differentiable and GPU-accelerated manner. This allows for end-to-end training and inference, including the data-driven Lagrangian coordinate system transformation of the data at runtime. We evaluate the model and compare it with other related AI-based models both quantitatively and qualitatively in an extreme event case study. Based on our evaluation, LUPIN matches and even exceeds the performance of the chosen benchmarks, opening the door for other Lagrangian machine learning models.