Abstract:

The article is devoted to our approaches to processing text in natural language to clarify the specific spatial relationship of objects and three-dimensional frame-by-frame visualization. The proposed approach allows us to show how the explicit constraints of the extracted spatial relationships affect and makes it possible to create possible layouts of objects on the scene. Natural language interpretations for spatial knowledge can generate three-dimensional scenes, which in turn are necessary to translate the scriptwriter's intent into the design of video games. The work also takes into account the rules of directing to create successful shots. Among them, accounting for the plan, camera rotation, as well as compositional nuances.

Abstract: This article considers approach to intelligent search of complex objects in different types of texts with structural markup which can be used for Big Data processing. We research two types of data entry: relational databases, which use their schemes as structural markup, and full-text scientific documents containing mathematical expressions (formulae). For such full-text documents we suggest additory automated markup to allow formula search. In both cases we use natural language texts, which are semistructured data, as data source for building ontology and conducting search at a later stage. For relational databases those are comments to table and table attribute names; for scientific documents (articles, monographs, etc.) it is a text content of marked up documents.

Abstract:

The problem of high and increasing cost of video game development is considered, and to solve it is proposed to apply procedural content generation, which will reduce development costs.

The work is a part of a large-scale research on automatic prototyping of video games and is devoted to the processing of game scenarios, i.e. natural language texts. It is proposed to extract the necessary entities from the scripts and pass them to further steps of the algorithm, which will generate game resources based on the textual descriptions.

There are several publications devoted to game text processing, in which several different structures for storing the extracted information are proposed. In this paper we propose a universal format that is suitable for processing the text of any video game and allows to create a corpus of texts for use in further research and automatic generation of game prototypes.

Abstract:

Cognitive abilities cover all higher human intellectual functions, including oral and written speech. The use of ellipses in writing is associated with the ability to clearly formulate a thought, avoiding the redundancy of its expression. Testing the ability to use ellipses can be the basis, on the one hand, for assessing the cognitive operation of generating ellipses in writing and detecting violations of this operation. This can serve as the basis for the early detection of dementia in medicine. On the other hand, such testing can be used to teach speech technologies, including in foreign languages. From a scientific point of view, it is important to determine the influence degree of training on the performance of text tasks. The article describes the development of a computer system for remote on-line testing the operation of converting a complete sentence into a sentence with an ellipsis of a certain type, the principles of evaluating the results of testing the subjects. The concept of the system is discussed. The structure of system and software development environment are described. A feature of the system is the creation of a new type of tasks related to natural language processing. The complexity of the development is determined by the need for automated formation of a bank of sentences’ pairs in natural language without ellipses and with ellipses of a certain type, which entails the inclusion, in the software environment, of text parsing tools and algorithms for automated formation of ellipses and / or restoration of complete sentences from elliptical ones. In conclusion, the prospects for the development and application of the proposed system are discussed.

Abstract:

The paper discusses the use of machine learning mechanisms, natural language analysis and intellectual search in the field of jurisprudence. The main expected results are the methodology for applying text-based analytics and semantic natural language processing (NLP) algorithms in knowledge management cases in different types of legal practice. The obtained results can be applied in the field of education and knowledge management in a wider context, since the study lies at the union of jurisprudence, mathematical and computer linguistics.

We describe a prototype of a multi-agent system of intellectual analysis of legal texts that is capable of identifying general dependencies on the existing database of legal documents, providing legal cases with similar topics, recommending the most likely outcomes of judicial review.