Automatsko strojno prevođenje sve je popularnija istraživačka tema u znanosti i raznim znanstvenim disciplinama, kao što su informacijske i komunikacijske znanosti, računarstvo, računalna lingvistika ...i sl. Razlog tome je prvenstveno to što danas omogućuje nezaobilaznu komunikaciju i brz prijenos informacija između različitih prirodnih jezika. To je posebno bitno za manje govorene jezike poput hrvatskoga, za koji još uvijek ne postoji dovoljan broj softverskih alata i digitalnih resursa potrebnih za razvoj specijaliziranih i kvalitetnih sustava za strojno prevođenje koji bi bili optimizirani za upotrebu u jednom specifičnom području. Sve brži rast količine podataka i sve veća potreba raznih dionika u sektorima industrije, gospodarstvu, znanosti, ali i u svakodnevnom životu ljudi impliciraju motivaciju za sistematiziranim i organiziranim razvojem te naknadnom prilagodbom sustava za automatsko strojno prevođenje za različite jezične parove. Budući da strojni prijevodi nisu savršeni, važno je primijeniti metode za računalno generiranje prijevoda prihvatljive razine kvalitete koja ovisi o samom zadatku i području primjene sustava za strojno provođenje. U ovom radu analiziran je model sustava za automatsko statističko strojno prevođenje, njegove komponente te uloga i značaj pojedinih elemenata unutar modela.
Informacije narušenog integriteta Dunđer, Ivan; Milas, Ante Josip
Međunarodne studije,
06/2023, Volume:
23, Issue:
1
Journal Article
Open access
U suvremenom informacijskom prostoru izloženi smo mnogobrojnim informacijama među kojima su i informacije narušenog integriteta. Iako manipulacije informacijama u javnom informacijskom prostoru nisu ...novost, njihova količina i brzina diseminacije putem internetskih društvenih mreža i komunikacijskih operativnih sustava predstavljaju novi izazov i ugrozu za nacionalnu sigurnost demokratskih država. U javnom prostoru se koristi nekoliko različitih termina kojima se nastoji objasniti da je integritet informacije plasirane u javni prostor bitno narušen što za posljedicu ima terminološko i kognitivno nerazumijevanje. Ovaj rad istražuje i teorijski određuje vrste informacija narušenog integriteta kao što su zlonamjerna i pogrešna informacija te dezinformacija. Potom rad prikazuje primjere institucionalnog suzbijanja širenja informacija narušenog integriteta na internetu i prikazuje ugrozu koju one predstavljaju za nacionalnu sigurnost demokratskih društava.
We consume much information in the current information realm, including integrity-breached information. Although information manipulation in the public sphere is not new, the volume and speed at which it spreads through online social networks and communication platforms pose a fresh challenge and threat to the security of democratic countries. To communicate that the integrity of published information is severely compromised, various terms are employed in the public, leading to terminological and cognitive misunderstanding. The integrity-breached information types, such as misinformation, malinformation, and disinformation, are examined and theoretically determined in this paper. The paper then provides examples of institutional challenges to tackling the dissemination of integrity-breached information on the internet and illustrates the threat they represent to the national security of democratic societies.
Automatic machine translation is an increasingly popular research topic in science and various scientific disciplines, such as information and communication sciences, computer science, computational ...linguistics etc. The reason for this is primarily that today it enables unavoidable communication and fast transfer of information between different natural languages. This is especially important for less spoken languages such as Croatian, for which there are still not enough software tools and digital resources that are needed for developing specialized and quality machine translation systems that would be optimized for use in one specific area. The evermore faster growth of data and the growing need of various stakeholders in the sectors of industry, economy, science, but also in peoples’ everyday life imply the motivation for the systematic and organized development and subsequent adaptation of automatic machine translation systems for different language pairs. Since machine translations are not perfect, it is important to apply methods for computationally generating translations of an acceptable level of quality that depends on the task itself and the scope of implementation of the machine translation system. In this paper, the model of a system for automatic statistical machine translation, its components and the role and significance of individual elements within the model are analyzed.
Machine translation is increasingly becoming a hot research topic in information and communication sciences, computer science and computational linguistics, due to the fact that it enables ...communication and transferring of meaning across different languages. As the Croatian language can be considered low-resourced in terms of available services and technology, development of new domain-specific machine translation systems is important, especially due to raised interest and needs of industry, academia and everyday users. Machine translation is not perfect, but it is crucial to assure acceptable quality, which is purpose-dependent. In this research, different statistical machine translation systems were built – but one system utilized domain adaptation in particular, with the intention of boosting the output of machine translation. Afterwards, extensive evaluation has been performed – in form of applying several automatic quality metrics and human evaluation with focus on various aspects. Evaluation is done in order to assess the quality of specific machine-translated text.
Politically polarizing issues are a growing concern around the world, creating divisions along ideological lines, which was also confirmed during the 2022 United States midterm elections. The purpose ...of this study was to explore the relationship between the results of the 2022 U.S. midterm elections and the topics that were covered during the campaign. A dataset consisting of 52,688 tweets in total was created by collecting tweets of senators, representatives and governors who participated in the elections one month before the start of the elections. Using unsupervised machine learning, topic modeling is built on the collected data and visualized to represent topics. Furthermore, supervised machine learning is used to classify tweets to the corresponding political party, whereas sentiment analysis is carried out in order to detect polarity and subjectivity. Tweets from participating politicians, U.S. states and involved parties were found to correlate with polarizing topics. This study hereby explored the relationship between the topics that were creating a divide between Democrats and Republicans during their campaign and the 2022 U.S. midterm election outcomes. This research found that polarizing topics permeated the Twitter (today known as X) campaign, and that all elections were classified as highly subjective. In the Senate and House elections, this classification analysis showed significant misclassification rates of 21.37% and 24.15%, respectively, indicating that Republican tweets often aligned with traditional Democratic narratives.
Parallel corpora have been widely used in the fields of natural language processing and translation as they provide crucial multilingual information. They are used to train machine translation ...systems, compile dictionaries, or generate inter-language word embeddings. There are many corpora available publicly; however, support for some languages is still limited. In this paper, the authors present a framework for collecting, organizing, and storing corpora. The solution was originally designed to obtain data for less-resourced languages, but it proved to work very well for the collection of high-value domain-specific corpora. The scenario is based on the collective work of a group of people who are motivated by the means of gamification. The rules of the game motivate the participants to submit large resources, and a peer-review process ensures quality. More than four million translated segments have been collected so far.
Strojno učenje te posebno pripadajuće potpodručje poznato kao duboko učenje pokreću novedisruptivne tehnologije i nedavna postignuća u različitim industrijama. Ovaj rad koristi do određenerazine istu ...tehnologiju pri izradi mobilne aplikacije za edukacijske svrhe, a koja omogućuje identifikacijunepoznatih zastava pomoću umjetne inteligencije. Kako bi aplikacija bila funkcionalna i efikasna,potrebno je bilo kreirati vlastiti podatkovni skup i obraditi ga na razne načine kako bi se osiguralazbirka podataka koja odražava podatke iz stvarnoga svijeta. Ova zbirka bi se potom koristila kaopodatkovni ulaz za razvijanje modela, koji se razvija unutar okruženja TensorFlow. Nakon što je modelrazvijen, implementiran je kao dio mobilne aplikacije programirane Flutterom. Funkcionalnost mobilneaplikacije i točnost modela ispitana je na brojci od preko 100 novih slika koje model prethodno nijevidio niti je nad njima bio treniran. Rezultat ovog ispitivanja mogao bi se smatrati odrazom okvirnespremnosti i primjenjivosti ove aplikacije u stvarnom svijetu.
Good and effective communication is in the common interest of the interlocutor, especially in a medical setting, which creates a specific relationship of trust, and directly influences the outcomes ...of a medical treatment. The aim of this research is to evaluate the role of information in creating communication feedback in the clinical practice of physiotherapists. To analyse the communication feedback of physiotherapists, a survey was conducted using a questionnaire on 471 physiotherapists employed in 74 healthcare institutions in Croatia. The research hypothesis in this paper assumes that there are no differences in the assessment of communication feedback among physiotherapists with regard to age and years of experience. However, the results show that there are significant differences in the assessment of communication feedback among physiotherapists. This is an important finding, which underlines that an issue that cannot be solved by medical knowledge alone can be resolved by effective communication when combined with a certain technique and way of communicating.
With the rapid development and great growth in popularity of video games, the video game industry has undergone a significant process of globalization in recent years. Video games are an essential ...factor in the digital entertainment industry today and attract many players, regardless of gender, age, social, political or economic status. This popularity and rapid development of video games is leading to the growing need for companies to make their video games available to as many people as possible in order to achieve a high return on fi nancial investments. Therefore, there is an obvious desire and need for video games to be tailored to all potential users, wherever they are. This is an extremely important factor in player satisfaction, and as such is very important in overcoming the language barrier, promoting the company’s international image and achieving good business results. But this means that the video game needs to be adapted to a large number of languages, cultural diff erences, ways of speaking and thinking, and at the same time to remove everything that is not suitable for the target market. One of the possible solutions for adapting to the international market is certainly localization, the application of which seeks to meet the needs of all players and markets. Video games, however, have specific features that distinguish them from other media, as they focus on player interactions and graphic elements of a game, which is unique compared to translating a novel or film. This paper provides an overview of video game adaptation strategies and the characteristics of the adaptation flow, with special emphasis on the localization approach as well as problems and open issues in the process of adapting video games to the international market.
Ease of access to and low cost of hardware and software for 3D scanning have made 3D technologies increasingly popular in recent research. One of the possible 3D scanning approaches is photogrammetry ...which relies on using a data set consisting of photographs of the same physical object. In this paper are evaluated different 3D models generated from the same input data set by specialised software packages for photogrammetry. The main attributes of the 3D models are examined in comparative analyses and their differences highlighted. Furthermore, visual qualitative inspections are performed on the models and the results are compared.