Computational Linguistics and Intelligent Systems. – 2022 р.
Permanent URI for this collectionhttps://ena.lpnu.ua/handle/ntb/56962
Періодичне видання за матеріалами конференції
It is our pleasure to present the proceedings of the Workshop Conference of COLINS-2022, the fourth edition of the International Conference on Computational Linguistics and Intelligent Systems, held in Lviv (Ukraine) on May 12-13, 2022. ISSN 2523-4013
Computational Linguistics and Intelligent Systems. – Lviv, 2022. – Volume 2 : Proceedings of the 6nd International conference, COLINS 2022. Workshop, Gliwice, Poland, May 12–13, 2022. – 306 p. – URL: https://colins.in.ua/wp-content/uploads/2022/07/VolumeII_Colins2022.pdf (дата звернення: 21.10.2022).
Browse
Search Results
Item Sarcasm definition in the comments of social networks(онлайн, 2022) Zanchak Maria; Vysotska VictoriaThe work aims to build a classifier of sarcasm using machine learning methods and NLP. A study was conducted with several ways of machine learning (Logistic Regression and Naive Bayesian Classifier) using the properties of TF-IDF and PoS and their combinations.Item Determining the mood in the lyrics of famous modern artists(онлайн, 2022) Zanchak Maria; Vysotska VictoriaThe article aims to compare the moods in the lyrics of famous modern artists of various genres (from pop to rap) and to understand what emotions dominate in the lyrics that listen to modern youth. The lyrics of three famous artists were chosen for this: Taylor Swift (due to his significant influence on pop culture in general), BTS (due to their significant influence on young people around the world), and Eminem (as a cult representative of rap culture).Item Information system for converting audio Ukrainian-language text into written one based on NLP methods and machine learning(онлайн, 2022) Tyshchuk Yuriy; Vysotska Victoria; Luchkevych MykhailoSpeech recognition provides various ways to analyse and process a user's recorded voice. It allows people to control different systems that are using one of the types of speech recognition. Speech-totext conversion is also a type of speech recognition that uses unscripted conversational data for further processing. This system involves several steps to process an audio file using electro-acoustic tools, sound filtering algorithms to find only relevant sounds, electronic datasets for the chosen language, and mathematical models that find appropriate words for a list of phonemes. People whose professions are related to typing large amounts of text using the keyboard can significantly speed up, facilitate the work process and reduce stress using systems that convert Speech-To-Text. In addition, such systems help businesses because remote work is becoming increasingly popular, and companies need tools for translating recorded audio from meetings to text for further analysis and systematization. The work's study object is converting audio in the Ukrainian language into its textual representation using NLP methods and machine learning. The scope of the research is audio file processing algorithms for finding relevant sounds and recognizing phonemes, as well as mathematical models for identifying words using an array of found phonemes. The work aims to design and develop an information system for converting audio in the Ukrainian language into its textual representation. According to the developments and calculations presented in work, namely: analysis of algorithms, areas of application and review of analogue problems in the first stage, the system analysis of the information system in the second stage and analysis and selection of relevant technologies and software development tools in the third stage, the information system for converting audio in the Ukrainian language into its textual representation was implemented in the form of a web application called «Ukrainian Speech-to-text», which is a technology for accurate and easy analysis of Ukrainian-language audio files and their other transcription into text. The application supports uploading files from the file system, recording them using a microphone, and saving the analysed data. The system is ready for use.Item Information system for forecasting sales of the range of building materials on the online trading platform based on the neural network tensor flow(онлайн, 2022) Semkiv Mykhaylo; Vysotska Victoria; Shakleina IrynaThis work is devoted to creating a system for forecasting sales of building materials numbers on the online trading platform based on the neural network Tensor flow. It was decided to develop an information-analytical system by building a tree of goals and analysing the hierarchy. The system is created as an application that runs in a web browser. The application will be available to everyone with the ability to add restrictions later. Sales forecasting is done by obtaining data from various APIs and working with ready-made data sets, allowing you to forecast the future product offer dates. To get a sales forecast, you need to enter data, train the model, validate our finished model and make a forecast.Item Information system of virtual reality tour of the ISN Department at LPNU with elements of full immersion as a platform for an open day(онлайн, 2022) Kuznyetsov Oleksiy; Vysotska Victoria; Luchkevych MykhailoVirtual reality (VR) is an important technology that allows significant progress to be made in under-covered areas. Immersive multimedia, or virtual reality, is a computer-simulated environment that can mimic a physical presence in the real or imagined world. Innovative applications, such as high-tech systems that integrate display technology, modelling technology, network technology, artificial touch technology, and computer graphics technology have made VR a breakthrough in technology. Virtual reality tours are one way to simulate a presence in a city where a person cannot be physically present at the moment. When viewing virtual tours with videos or photos, a person sees only a flat image and cannot interact with it. Thus, the effect of the fact that it is present in that place is lost. Virtual reality, with the result of complete immersion, eliminates these disadvantages almost completely and allows you to interact with objects located in the virtuality of the scene with the natural movements of your body. In addition, in a short period, with her help, she can visit many places without leaving home, which in real life cannot be done because you need to get to certain areas, which takes time. The research's objective is to conduct an interactive virtual reality tour of the ISN Department of LPNU. The research subject is the means and methods of designing and developing information systems for the virtual reality tour of the ISN Department of LPNU. The practical significance of the obtained results is the implemented information system of the interactive tour of the ISN Department of LPNU. The scientific novelty of the obtained results is the information system of virtual reality, which is designed for a tour of the ISN Department of LPNU with elements of complete immersion as a platform for an open day.Item The scientific degree determination of the scientific and technical text author(онлайн, 2022) Konyk Myroslav; Vysotska VictoriaThis article discusses the main methods used to solve classification problems and texts to determine the scientific degree of the author of scientific and technical text. A data set was taken to classify and cluster the text containing scientific articles from different fields.Item Information system for sounding Ukrainian-language text based on NLP methods and machine learnin(онлайн, 2022) Byelousov Illya; Vysotska Victoria; Shakleina IrynaThis work is devoted to developing an information system for sounding Ukrainian-language text based on NLP methods and machine learning. The authors analyzed the pros and cons of the implemented software solutions for the Ukrainian-language text and took them into account during the implementation of the information system. Methods and frameworks that ensure theapplication's correct, fast and stable operation are also described. A user manual has been created for the correct use of the created system. All processes of using the program are shown, and the control example for productivity confirmation and work of the program is analyzed.Item Multilingual voice user’s messages recognising and translating based on telegram bot and speech-to-text technology(онлайн, 2022) Aksonov Denys; Vysotska VictoriaConverting users’ voice messages into text is an urgent task because it is very convenient. Many people send voice messages because it saves users time. After all, writing text by hand is a longer process than recording a voice. But there are cases when the people to whom thevoice message was sent do not have the opportunity to listen to it. It becomes a severe problem when the user thinks there may be something fundamental in this message, and the thought of it will not give him peace of mind until he can listen to it. At this point, a telegram bot that I will develop during this course may come to the rescue. The user will send the received voice message to the Bot, which with its functionality, will convert the voice into text, which will be sent to the user after the conversion. It allows the user to learn about the contents of the voice message without listening to it. The object of further research is the conversion of users’ voice messages into text. The study subject is to send a message with the text that will be received as a voice message conversion result that will be received from the Bot user.Item Telegram bot development based on with text-to-speech functions and text recognition from an images(онлайн, 2022) Aksonov Denys; Vysotska VictoriaThe goal is to develop a telegram bot that will have the functionality to convert text to voice message and recognise text from images. Currently, photo text recognition is an urgent task. It will expand the functionality of the telegram even more, and people can receive the finished text without leaving the application and without using different services for this, which takes more time. The object of further research is the process of text converted into a voice message and the recognition of text from images. The research subject is methods and tools to receive a message with text that will be read from a picture sent by the user and accept a voice message in response to the text sent by the user. Not many telegram bots can recognise text from a photo or convert text to a voice message, but no bot can perform these two functions simultaneously. It indicates that this Bot will be able to interest people with its scientific novelty, increasing the total number of its users.