Collocations have been the subject of much scientific research over the years. The focus of this research is on a subset of collocations, namely metaphorical collocations. In metaphorical ...collocations, a semantic shift has taken place in one of the components, i.e., one of the components takes on a transferred meaning. The main goal of this paper is to review the existing literature and provide a systematic overview of the existing research on collocation extraction, as well as the overview of existing methods, measures, and resources. The existing research is classified according to the approach (statistical, hybrid, and distributional semantics) and presented in three separate sections. The insights gained from existing research serve as a first step in exploring the possibility of developing a method for automatic extraction of metaphorical collocations. The methods, tools, and resources that may prove useful for future work are highlighted.
Kolokacije su već dugi niz godina tema mnogih znanstvenih istraživanja. U fokusu ovoga istraživanja podskupina je kolokacija koju čine metaforičke kolokacije. Kod metaforičkih je kolokacija kod jedne od sastavnica došlo do semantičkoga pomaka, tj. jedna od sastavnica poprima preneseno značenje. Glavni su ciljevi ovoga rada istražiti postojeću literaturu te dati sustavan pregled postojećih istraživanja na temu izlučivanja kolokacija i postojećih metoda, mjera i resursa. Postojeća istraživanja opisana su i klasificirana prema različitim pristupima (statistički, hibridni i zasnovani na distribucijskoj semantici). Također su opisane različite asocijativne mjere i postojeći načini procjene rezultata automatskoga izlučivanja kolokacija. Metode, alati i resursi koji su korišteni u prethodnim istraživanjima, a mogli bi biti korisni za naš budući rad posebno su istaknuti. Stečeni uvidi u postojeća istraživanja čine prvi korak u razmatranju mogućnosti razvijanja postupka za automatsko izlučivanje metaforičkih kolokacija.
Neki zvučni zapisi čine arhivsko gradivo, predstavljaju kulturno dobro i dio su nacionalne baštine te se kao takvi trebaju zaštititi i biti dostupni široj javnosti. Najbolji način za očuvanje uz ...osiguranje dostupnosti je njihovo arhiviranje. Ovaj članak bavi se važnim aspektima arhiviranja zvučnih zapisa. Najprije su pojašnjeni osnovni pojmovi, dane su uvodne natuknice, kratki povijesni pregled stvaranja zvučnih zapisa,nabrojane su i opisane vrste zvučnih zapisa prema nosaču na koji su pohranjeni, pojašnjena je uloga zvučnih zapisa kao informacija i kao arhivskog i kulturnog dobra. Zatim su u drugom poglavlju opisana načela i strategije za očuvanje zvučnih zapisa: koraci od kojih se sastoji postupak arhiviranja zvučnih zapisa, karakteristike medija za pohranu zvučnih zapisa s obzirom na njihovu nestabilnost, zastarijevanje i osjetljivost na vanjske utjecaje te najbolji uvjeti za njihovo očuvanje, ukratko je pojašnjen postupak digitalizacije zvučnih zapisa i karakteristika ciljnog formata zvučnih zapisa sa svrhom njihova arhiviranja. Slijedi poglavlje koji se bavi najpoznatijim standardima za opis zvučnih zapisa. Također je prikazan uzorak za opis zvučnih zapisa i primjer opisa zvučnog zapisa. U posljednjem poglavlju govori se o stanju u Hrvatskoj s aspekta stanja zvučnih zapisa i njihova arhiviranja.
It is very popular today to integrate voice interfaces into IoT devices. The pronunciation and proper prosody of speech play a major role in the intelligibility and naturalness of synthesized voices. ...Each language has its own prosodic characteristics. In this paper, we present the results of a study aimed at testing the applicability of methods for modelling and predicting the prosodic features of the Croatian language. The extent to which their performance can be improved by incorporating linguistic features and linguistic peculiarities specific to the Croatian language was investigated. In the model learning process, tree classification was used to predict the lexical stress position and the type of stress in a word, and a lexicon of 1,011,785 word forms was used as the model learning set. Separate models were created for predicting the position and type of lexical stress. The results improved significantly after the rules for atonic words (clitics) were applied. A hybrid approach combining a rule-based approach and a modelling approach was also proposed. The final accuracy of assigning lexical stress using the hybrid approach was 95.3%.
The aim of this paper is to evaluate the quality of popular machine translation engines on three texts of different genre in a scenario in which both source and target languages are morphologically ...rich. Translations are obtained from Google Translate and Microsoft Bing engines and German-Croatian is selected as the language pair. The analysis entails both human and automatic evaluation. The process of error analysis, which is time-consuming and often tiresome, is conducted in the user-friendly Windows 10 application TREAT. Prior to annotation, training is conducted in order to familiarize the annotator with MQM, which is used in the annotation task, and the interface of TREAT. The annotation guidelines elaborated with examples are provided. The evaluation is also conducted with automatic metrics BLEU and CHRF++ in order to assess their segment-level correlation with human annotations on three different levels–accuracy, mistranslation, and the total number of errors. Our findings indicate that neither the total number of errors, nor the most prominent error category and subcategory, show consistent and statistically significant segment-level correlation with the selected automatic metrics.
Ljudsko djelovanje u 21. stoljeću, pod utjecajem je 4. industrijske revolucije koja na dnevnoj bazi mijenja način na koji društvo živi, napreduje i egzistira. Neočekivanom pojavom pandemije, kao ...pozitivan odgovor, uslijedila su brojna digitalna rješenja koja su potaknula još veći razvoj i promet, kako web tako i mobilnih aplikacija te ostalih digitalnih rješenja. Glavni cilj ovog rada je istražiti postupke digitalizacije, digitalnih rješenja, tehnologija i aplikacija koje su se koristile tijekom pandemije te ukazati na napredak digitalnih rješenja razvijenih u novim, nepoznatim okolnostima kao i identificirati moguće izazove u njihovom daljnjem razvoju i primjeni te predložiti moguća rješenja. U radu se opisuje uloga tehnologije u olakšavanju svakodnevnih aktivnosti u izvanrednim okolnostima te se identificiraju prednosti i mogući izazovi u primjeni digitalnih rješenja u takvim okolnostima. U tu se svrhu opisuju najutjecajnije web aplikacije i digitalne tehnologije te njihova uloga u osiguranju normalnog tijeka života u izazovnim vremenima.
Human activity in the 21st century is under the influence of the fourth industrial revolution, which is changing the way society lives, develops and exists on a daily basis. The unexpected appearance of the pandemic as a positive reaction was followed by numerous digital solutions that stimulated even greater development and traffic, both web and mobile applications and other digital solutions. The main objective of this paper is to examine digitalization processes, digital solutions, technologies and applications used during the pandemic and to show the progress of digital solutions developed under new, unknown circumstances, as well as to identify possible challenges in their further development and application and to propose possible solutions. The paper describes the role of technology in facilitating everyday activities in exceptional circumstances and highlights the benefits and potential challenges of applying digital solutions in such circumstances. It describes the most influential web applications and digital technologies and their role in ensuring the normal course of life in difficult times.
The introduction and verification of new teaching methods is of utmost importance nowadays since new generations of students evidently grow up and communicate differently from their predecessors. The ...aim of this work is to inspect the prospects and possibilities of integrating karaoke into the primary school classroom. The paper explores attitudes toward karaoke as a teaching method in relation to gender, age, and musical skills, aiming to identify ideal target group. General student and teacher attitudes toward karaoke are also examined, as well as teacher attitudes with respect to demographic data such as gender and field of education. Based on the findings of the conducted research, the paper proposes strategies which enable efficient integration of karaoke into the classroom by increasing students' motivation and their satisfaction with education.
This paper presents an overview of selected clustering models and shows an application of K-Means algorithm to document clustering. In the introductory part, the definitions of basic concepts and ...common characteristics of clustering models are described. Then an overview of clustering models is given. The methods of clustering, basic characteristics, visualization and possible input data for each algorithm are presented. The authors also explain the assessment of each algorithm taking into consideration measures such as Rand index, homogeneity completeness, V-measure and Silhouette coefficient. Furthermore, the paper describes the application of the K-Means algorithm to document clustering showing the final result and elaborating the procedures applied when clustering the documents.
The aim of the paper is to examine the possibilities for automatic generation of language learning exercises and compare them to those manually compiled by language instructors. The paper first ...presents a universal methodology applied in manually created exercises for learning the language for specific purposes, elaborated with examples in the field of academic English. Next, the automation of the procedure is explored through a series of steps which include creating the corpus, analysing each exercise type and the possibility of its automatic generation, automatically generating the exercise, and evaluating the end result. The results of the evaluation suggest that automatic generation of exercises can serve as a preliminary step of a two-stage process of exercises development in which each exercise, however, needs additional approval from the language expert.
The aim of the paper is to examine the possibilities for automatic generation of language learning exercises and compare them to those manually compiled by language instructors. The paper first ...presents a universal methodology applied in manually created exercises for learning the language for specific purposes, elaborated with examples in the field of academic English. Next, the automation of the procedure is explored through a series of steps which include creating the corpus, analysing each exercise type and the possibility of its automatic generation, automatically generating the exercise, and evaluating the end result. The results of the evaluation suggest that automatic generation of exercises can serve as a preliminary step of a two-stage process of exercises development in which each exercise, however, needs additional approval from the language expert.