Computational linguistics and intelligent systems. – 2018 р.

Permanent URI for this collection

https://ena.lpnu.ua/handle/ntb/42549

Proceedings of the 2nd International conference, June 25–27, 2018, Lviv

This volume represents the proceedings of the Workshop Conference, with Posters and Demonstrations track, of the 2nd International Conference on Computational Linguistics and Intelligent Systems, held in Lviv, Ukraine, in June 2018. It comprises 19 contributed papers that were carefully peer-reviewed and selected from 36 submissions. The volume opens with the abstracts of the keynote talks. The rest of the collection is organized in two parts. Parts II contain the contributions to the Workshop COLINS Conference tracks, structured in two topical sections: (I) Computational Linguistics; (II) Intelligent Systems.

Computational linguistics and intelligent systems : proceedings of the 2nd International conference, 25–27 June 2018 / Lviv Polytechnic National University. – Lviv, 2018. – Volume 2 : Workshop. – 178 p.

Зміст


1
5
10
PART 1. KEYNOTE SPEAKERS TALKS
17
28
40
53
60
71
81
PART 2. WORKSHOP CONFERENCE TRACKS. SECTION I. COMPUTATIONAL LINGUISTICS
97
108
110
112
114
122
SECTION II. INTELLIGENT SYSTEMS
129
139
146
157
161
171
177

Content (Vol. 2 : Workshop)


1
5
10
PART 1. KEYNOTE SPEAKERS TALKS
17
28
40
53
60
71
81
PART 2. WORKSHOP CONFERENCE TRACKS. SECTION I. COMPUTATIONAL LINGUISTICS
97
108
110
112
114
122
SECTION II. INTELLIGENT SYSTEMS
129
139
146
157
161
171
177

Browse

Recent Submissions

Now showing 1 - 20 of 23
  • No Thumbnail Available
    Item
    The uantitative research of scientific texts at the symbolic level
    (Lviv Polytechnic National University, 2018-06-25) Kulchytskyi, Ihor; Shandruk, Ulyana; Lviv Polytechnic National University, Lviv, Ukraine
    The concept of text has been one of the important aspects of the scientific research since the beginning of the last century. It has been incorporated in the scientific paradigms of various fields of human knowledge such as psychology, philosophy, science of culture, linguistics, pedagogy. The researchers call this terms interdisciplinary and they claim it to be one of the key concepts in the field of culture of language, linguistics, and communicative linguistics. Text is a unit of a written language that is used by immense audience, therefore, the difficulties of communication are growing with the increase in the number of people who actually communicate. So, the concept of text in linguistics has always remained one of the least investigated. The paper aims to contribute into the research of text in general and scientific text in particular and reveal if any the connection between the usage of symbols and the genre the investigated text belongs to.
  • No Thumbnail Available
    Item
    The Typhlocomments Rules for Audiodescription System of the Video Content Formation for People with Visual Impairments
    (Lviv Polytechnic National University, 2018-06-25) Demchuk, Andriy; Lozynska, Olga; Information Systems and Networks Department, Lviv Polytechnic National University, Lviv
    This paper introduces the rules of constructing typhlocommentars for audiodescription system of the video content formation for people with visual impairments. This system can be considered as an intermediary between the available video content from the one side and the visually impaired user from the other. The process of forming the rules of typhlocomments is discussed. This rules are formed in the form of a proposal function, the truth of which is verified on the facts and the rules obtained as a result of psychological research. The use case diagram that describes the functional appointment of the system is suggested. The resulting use case diagram contains seven cases for use and two actors, among which the inclusion and extension relations are set. Tasks that require further research are defined.
  • No Thumbnail Available
    Item
    Sentiment analysis of the US and Ukrainian presidential speeches
    (Lviv Polytechnic National University, 2018-06-25) Dilai, Marianna; Onukevych, Yuliya; Dilay, Iryna; Applied Linguistics Department, Lviv Polytechnic National University; Lviv, Ukraine
    The paper presents the results of the sentiment analysis of the US and Ukrainian presidential speeches. By means of SentiStrength and UAM Corpus Tool programs, we attempt to extract opinions and sentiments in the speeches of Donald Trump and Petro Poroshenko. The main contribution of this study is the adaptation of the SentiStrength program to the Ukrainian language by compiling a political domain glossary of the Ukrainian emotion-bearing words. Furthermore, we compare lexical means of sentiment expression in the analyzed texts.
  • No Thumbnail Available
    Item
    Methods of information resources processing in virtual library
    (Lviv Polytechnic National University, 2018-06-25) Rusyn, Bohdan; Vysotska, Victoria; Pohreliuk, Liubomyr; Kazimierz Pulaski University of Technology and Humanities in Radom, Poland; Lviv Polytechnic National University, Lviv, Ukraine; Karpenko Physico-Mechanical Institute of the NAS Ukraine
    The thesis discusses the development of unified methods and software tools for processing information resources in Virtual Library as example the electronic content commerce systems (ECCS). A model of Virtual Library Systems (VLS) is proposed. The models of information resource processing in ECCS are proposed. Architecture and models of VLS are built. A new approach to application and implementation of business processes is formulated for the construction of VLS. A complex method of content creation, the operational method of content management and complex method of content support are developed. Design and implementation methods of VLS are based on online newspapers, which reflect the results of theoretical research, are developed. From the perspective of a systemic approach, the principles of applying information resources processing in electronic content commerce systems for content lifecycle implementation made the development of methods for the content formation, management and support possible. An integrated method of content formation for the time and resources reduction of content production is developed. A method of content management for the time and resources reduction of content sales was created, which makes it possible to implement content management subsystem. A method of content support for the time and resource reduction of the target audience analysis in VLS is implemented, which makes it possible to develop a content support subsystem.
  • No Thumbnail Available
    Item
    SEO technology for Web-Resource processing
    (Lviv Polytechnic National University, 2018-06-25) Chyrun, Lyubomyr; Vysotska, Victoria; Chyrun, Liliya; Gozhyj, Aleksandr; Kalinina, Iryna; Lviv Polytechnic National University, Lviv, Ukraine; Petro Mohyla Black Sea National University, Mykolayiv, Ukraine
    The thesis to the methods of elaborating Web-resources in electronic commercial content systems is devoted. The methods of formation and maintenance of commercial Web-content were developed and the method of the management of commercial Web-content based on SEO technology are improved.
  • No Thumbnail Available
    Item
    Ontology using for decision making in a competitive environment
    (Lviv Polytechnic National University, 2018-06-25) Lytvyn, Vasyl; Oborska, Oksana; Vysotska, Victoria; Dosyn, Dmytro; Demchuk, Andriy; Lviv Polytechnic National University, Lviv, Ukraine; Silesian University of Technologyty, Gliwice, Poland; Karpenko Physico-Mechanical Institute of the NAS Ukraine
    A method of decision making system elaboration in competitive environment based on ontological approach was developed. The models based on a hinged Boyd-Moore automaton. State machine loops are the stages Boyd and filling processes, ontology editing and a search of relevant knowledge ontology. Possible transitions between the states of the machine and transfer parameters between them were determined. For a quantitative modeling of decision support process in a competitive environment, mathematical support and methods of domain-specific ontology in the Boyd cycle (OODA – observation, orientation, decision, action) were elaborated. Thus, for the military at an “Observations” stage intelligence domain ontology determining of the strengths and weaknesses of the enemy. At the stage of “orientation”, ontological data are used for simulation of possible realizations of the battle and for optimal positioning of the forces. For “Resolution” stage, target distribution was developed using a method based on genetic algorithms, which helped to reduce the computational complexity of finding effective distribution targets. Ontology expertise based on descriptive logic is presented to increase the effectiveness of possible solutions.
  • No Thumbnail Available
    Item
    Study methods of image segmentation for intelligent surveillance systems
    (Lviv Polytechnic National University, 2018-06-25) Hrytsyk, V. V.; Lviv Polytechnic National University, Lviv, Ukraine
    The research of the machine-machine interface element is presented for the possibility of dynamic adaptation to improve the perception of the very least environment by developing a technique for adapting the robovision. The study include comparing between different threshold methods of segmentation of images of different categories.
  • No Thumbnail Available
    Item
    Author index
    (Lviv Polytechnic National University, 2018-06-25)
  • No Thumbnail Available
    Item
    Зміст до "Computational inguistics and Intelligent systems"
    (Lviv Polytechnic National University, 2018-06-25)
  • No Thumbnail Available
    Item
    Peculiarities of remote-piloted vehicles on-board navigation complex construction
    (Lviv Polytechnic National University, 2018-06-25) Mykyichuk, Mykola; Markiv, Volodymyr; Lviv Polytechnic National University, Lviv, Ukraine
    The article dwells upon the peculiarities of on-board navigation complex construction. It is highlighted that the optimal method for constructing on-board navigation complex is integration into single complex of sensors and systems with the integration of measurement information. The core of on-board navigation complex should be built on the basis of free-form inertial navigation system. To ensure the piloting tasks, the on-board equipment includes system of air signals. On the basis of the air signals system and magnetic compass air course counting is performed, which together with the inertial calculation allow to obtain comprehensive solution in an autonomous mode. It is important to include in the on-board navigation complex receiver of GNSS signals. Thus, the ideology of constructing the on-board navigation complex initially consists in the integration of measurements from the sensors and systems that make up its structure. It is emphasized that directly on-board navigation complex consists from inertial sensors, GNSS and magnetic compass receivers and also interface with air signal system. Specific types of sensors and systems are selected in accordance with the requirements of software and algorithmic support of onboard navigation complex.
  • No Thumbnail Available
    Item
    Using dynamic neural networks for server load prediction
    (Lviv Polytechnic National University, 2018-06-25) Pukach, Pavlo; Hladun, Volodymyr; Lviv Polytechnic National University, Department of Applied mathematics
    In this paper, the approach of using neural networks for making time series predictions of strongly nonlinear data is used. A brief examination of neural networks usage for time series predictions is given, as well as the definition and schematics of LSTM blocks. The comparison between the time delay values and the prediction accuracy is given. It is shown that certain values of time delay can greatly increase the prediction accuracy.
  • No Thumbnail Available
    Item
    Committees
    (Lviv Polytechnic National University, 2018-06-25)
  • No Thumbnail Available
    Item
    Influence of readability on popularization of internet resources
    (Lviv Polytechnic National University, 2018-06-25) Basyuk, Taras; Lviv Polytechnic National University, Lviv, Ukraine
    The article analyzes the influence of readability of the content on the popularization of Internet resource. The analysis of known methods for content readability determination, as additional component of popularization has been carried out. In researching, an algorithm for determining the basic level of readability has been developed, and recommendations for its application have been provided in order to enter the TOP results query. The question of determining the parameters of graphic design of the content is considered and recommendations on their application in the process of designing the Internet resource are provided. The research conducted creates the preconditions for further study of the subject and formation of mathematical support for automatic content rewriting depending on the required level of readability.
  • No Thumbnail Available
    Item
    Extracting and classification the semi-structured data of web-systems
    (Lviv Polytechnic National University, 2018-06-25) Pelekh, Irina; Lviv Polytechnic National University, Lviv, Ukraine
    The extracting and classification of semi-structured data of websystems is described. The definition of semi-structured data is given and the main characteristics are defined. The variety of tasks text information processing is grouped into the eleven large classes related to the analysis of text data. The traditional models of knowledge representation are considered. An algorithm for the web-sources, from which data will to be obtained, ontological model integrating creating is proposed. The process of data extracting using the query language to the markup language elements is characterized.
  • No Thumbnail Available
    Item
    Reverse-search system of similar or identical images
    (Lviv Polytechnic National University, 2018-06-25) Veres, Oleh; Kis, Yaroslav; Kugivchak, Vladyslav; Rishniak, Igor; Information Systems and Network Department, Lviv Polytechnic National University
    The article algorithms of image analysis on the number of errors of operation are investigated. The prototype of the system was created, and testing of the described methods was carried out. The result of the analysis became the basis for the information system project of reverse search of similar or identical images.
  • No Thumbnail Available
    Item
    The information system for identification of content set based on analysis of similar texts
    (Lviv Polytechnic National University, 2018-06-25) Kovalchuk, Viktoriia; Lytvyn, Vasyl; Vysotska, Victoria; Hrendus, Mariya; Naum, Oleh; Lviv Polytechnic National University, Lviv, Ukraine; Silesian University of Technologyty, Gliwice, Poland; Drohobych Ivan Franko State Pedagogical University, Drohobych, Ukraine
    Information search is one of the most dynamic areas in terms of development and search for new algorithms for solving this problem. Nowadays a large number of search engines, which work with artistic composition, have been developed, but most of them are oriented only on conducting the work with metadata. In addition, effective methods of analysis of the subject of the text have been used, as well as identification of works after it is considered. Different ways of searching and problems of implementation of an ontologically flexible semantic search are considered. An information system for the identification of a plurality of content has been developed based on a thematic analysis of similar texts.
  • No Thumbnail Available
    Item
    Distinguishing between natural and random texts: a statistical measure linked to word clustering
    (Lviv Polytechnic National University, 2018-06-25) Kushnir, O. S.; Kashuba, A. I.; Yaremkiv, V. V.; Optoelectronics and Information Technologies Department
  • No Thumbnail Available
    Item
    Embedding speech recognition tools for custom software: Engines Overview
    (Lviv Polytechnic National University, 2018-06-25) Dovbysh, Arthur; Alieksieiev, Vladyslav; Department of Applied Mathematics, Lviv Polytechnic National University
    Different solutions and tools for speech recognition are now available. Nevertheless, implementation of natural language processing still remains a current problem. Developing any custom software with a good style of UI/UX requires the integration of speech recognition. Evidently, the most common solution is to use some engine as an embedded standard tool. Here in the paper we are presenting an overview and an analysis of some popular speech recognition engines: Google Speech Recognition API, Microsoft Speech API, Yandex Speech Kit and Julius. These speech recognition tools are a readyto- serve and suitable to supplement your own software with a reliable voice command detection or voice control feature. The results of our analysis comes from an experiment of voice recognition using these tools as an embedded component in a custom software.
  • No Thumbnail Available
    Item
    Method for automatic collocation extraction from Ukrainian corpora
    (Lviv Polytechnic National University, 2018-06-25) Kuzmina, Maria; Petrasova, Svitlana; National Technical University "Kharkiv Polytechnic Institute"
  • No Thumbnail Available
    Item
    DFA method for the analysis of Long-Range Correlations: Application to Statistical Linguistics
    (Lviv Polytechnic National University, 2018-06-25) Ivanitskyi, L. B.; Kushnir, O. S.; Optoelectronics and Information Technologies Department