Претрага

Упит dcterms_subject_txt:Industrial and Manufacturing Engineering

2378 items

  • History of meteorite donations to the Collection of Minerals and Rocks of the University of Belgrade, Faculty of Mining and Geology (Serbia)

    Alena Zdravković, Maja Milošević, Kristina Šarić, Ivana Jelić, Ana Černok (2021)
    ... Čačak in 1919, and Dimitrovgrad in 1947), contributed to further developments of meteorite collections and increased the potential for sample exchanges with foreign museums. Prof. Josif Pančić was a very active and respected scientist across Europe, and with his collaborations and private efforts ...
    ... Mining and Geology (UBFMG) contains 52 meteorites organized in two collections: 36 samples are stored in the Collection of Minerals and Rocks and 16 pieces are kept in the Paleontological Collection. In this paper we describe the collection of meteorites at the Collection of Minerals and Rocks, ...
    ... 202 g and P81 Fe-meteorite 48.8 g), and one obviously non-iron meteorite sample that is still unclassified (11.5 cm long). The significance of preserved meteorite specimens in old university collections such as the Collection of Minerals and Rocks at UBFMG is huge both from historical and scientific ...

  • Projecting short to medium-term effects of carbon emissions trading on Serbia's GDP

    Boban Pavlović, Nikola Trtica (2024)
    This paper presents an approach to assess the short to medium-term effects of the Emissions Trading System (ETS), an economic and climate policy instrument aimed at reducing greenhouse gas emissions, on GDP from the expenditure side. The analysis focuses on Serbia’s electricity sector, which relies heavily on lignite-based pro duction dominated by state-owned enterprises. The obtained projections suggest that in the short term, the introduction of an ETS may lead to slower GDP growth compared to official forecasts. However, ...
    ETS, BDP - rashodni pristup, cene električne energije
    ... l-drive-costs-high er-and-emissions-lower. (Accessed 10 April 2024). Csereklyei, Z., 2020. Price and income elasticities of residential and industrial electricity demand in the European Union. Energy Pol. 137, 111079. https://doi.org/10.1016/ j.enpol.2019.111079. Dagoumas, A.S., Polemis, M.L. ...
    ... Europe, including all 27 EU Member States (EU-27), as well as Iceland, Liechtenstein, and Norway (part of the European Economic Area (EEA)). It regulates approximately 10,000 power stations and industrial facil- ities, constituting: around . 40% of the EU's total GHG emissions (Dechezlepretre ...
    ... tre et al., 2023). Since 2005, the EU ETS has reduced emissions in covered sectors (electricity production, most industrial production, and intra-EEA flights) by approximately 43%, aiding in meeting the 2020 EU target. In contrast, emissions in sectors not covered by the EU ETS were only 16% ...

  • OntoLex Publication Made Easy: A Dataset of Verbal Aspectual Pairs for Bosnian, Croatian and Serbian

    Ranka Stanković, Maxim Ionov, Medina Bajtarević, Lorena Ninčević (2024)
    Ovaj rad predstavlja novi jezički resurs za pretraživanje i istraživanje verbalnih aspektnih parova u BCS (bosanskom, hrvatskom i srpskom), kreiran korišćenjem principa Lingvističkih Povezanih Otvorenih Podataka (LLOD). Pošto ne postoji resurs koji bi pomogao učenicima bosanskog, hrvatskog i srpskog kao stranih jezika da prepoznaju aspekt glagola ili njegove parove, kreirali smo novi resurs koji će korisnicima pružiti informacije o aspektu, kao i link ka aspektnim parovima glagola. Ovaj resurs takođe sadrži spoljne linkove ka monolingvalnim rečnicima, Wordnetu i BabelNetu. ...
    aspekt glagola, lingvistički otvoreni podaci, BCS

  • Development and Evaluation of Three Named Entity Recognition Systems for Serbian - The Case of Personal Names

    Branislava Šandrih, Cvetana Krstev, Ranka Stanković (2019)
    In this paper we present a rule- and lexicon-based system for the recognition of Named Entities (NE) in Serbian news paper texts that was used to prepare a gold standard annotated with personal names. It was further used to prepare training sets for four different levels of annota tion, which were further used to train two Named Entity Recognition (NER) sys tems: Stanford and spaCy. All obtained models, together with a rule- and lexicon based system were evaluated on ...
    NER, Named Entity Recognition Systems, Serbian, Personal Names
    ... are three categories of NER systems: 1) The rule-based (RB) (Krupka and Hausman, 1998; Friburger and Maurel, 2004); 2) the Ma- chine Learning (ML) based (Finkel and Manning, 2009; Singh et al., 2010); and 3) hybrid meth- ods (Jansche and Abney, 2002). The ML-based methods can often be “black boxes”, in ...
    ... appli- cation that enables NER across many languages and domains),1 OpenNLP (rule-based and statisti- cal NER),2 spaCy (Honnibal and Montani, 2017) (module written in Python, used for advanced NLP)3 and many others. For Serbian, thus far a rule-based and lexicon-based NER system was developed – SRPNER (Krstev ...
    ... expressions (date and time, and 3) name expressions (personal, geopo- litical and organization names). The system was designed in a form of the cas- cades of Finite-State Transducers (FST) in which every transducer recognizes and tags a certain class of NEs (Friburger and Maurel, 2004; Mau- rel et al ...

  • Approach to operational mine planning: Case study Tamnava West

    Dejan Stevanović, Mirjana Banković, Milica Pešić Georgiadis, Ranka Stanković (2014)
    ... many analysis of the technical and economic parameters and detailed planning of all possible scenarios of production. Due to availability of the coal resources and their price stability, coal is and will retain its important role in power generation in Europe and worldwide 1. In Serbia, coal ...
    ... integrated geology and mine planning solutions. It is comprehensive tool specialized for coal and other stratified deposits, such as phosphate, zinc, bauxite, iron ore, and platinum. Minex covers almost every part of geological modeling and mine planning process. It provides a fast and powerful set ...
    ... within Minex called the "Splitting" and "Father and Son" concept was applied and the gridding mesh size was set at 25 m x 25 m to cover all boreholes. An exceptionally large scan distance of 35,000m was selected for seam General Purpose interpolation, and for assay data Inverse Distance, power ...

  • SASA Dictionary as the Gold Standard for Good Dictionary Examples for Serbian

    Ranka Stanković, Branislava Šandrih, Rada Stijović, Cvetana Krstev, Duško Vitas, Aleksandra Marković (2019)
    У овом раду представљамо модел за избор добрих примера за речник српског језика и развој иницијалних компоненти модела. Метода која се користи заснива се на детаљној анализи различитих лексичких и синтактичких карактеристика у корпусу састављених од примера из пет дигитализованих свезака речника САНУ. Почетни скуп функција био је инспирисан сличним приступом и за друге језике. Дистрибуција карактеристика примера из овог корпуса упоређује се са карактеристиком дистрибуције узорака реченица ексцерпираних из корпуса који садрже различите текстове. Анализа је показала да ...
    Српски, добри примери из речника, аутоматизација израде речника, издвајање својстава, Машинско учење
    ... various lexical and syntactic features of the gold standard examples, classified them and compared the results with the control corpus (both gold and control corpus are presented in Section 4). The initial set of features was inspired by Kilgarriff et al. (2008) and Kosem (2017), and guided by rec ...
    ... ) in the sentence; and since examples should help the understanding of the definition, they must be easy to understand – which means that their syntactic structure should be simple and their lexis not too difficult and uncommon. Informativeness, typicality with naturalness, and intelligibility are ...
    ... while 5% had an insertion but were not shortened and 2% had both insertions and shortenings. The number of editorial examples was relatively small, and we have not used these in our test set. 2.3.5 What should a good example contain? As Atkins and Rundell (2008) point out, there is plenty of evidence ...

  • Anisotropic grossular–andradite garnets: Evidence of two stage skarn evolution from Rudnik, Central Serbia

    Bojan Kostić, Danica Srećković-Batoćanin, Petyo Filipov, Pavle Tančić, Kristijan Sokol (2021)
    This paper presents LA-ICP-MS data for garnets from the Rudnik skarn deposit (Serbia), which range from Grs45–58Adr40–52Alm2–3 in the core and Adr70–97Grs2–29Sps1 in the rim displaying anisotropy and zoning. In spite of wide compositional variations the garnets near the end-member of andradite (Adr > 90) are generally isotropic. Fe-rich rims exhibit LREE depletion and flat HREE pattern with weak negative Eu anomaly, including higher As and W contents. On the other side, the Fe-poorer core shows flat REE pattern ...
    grandite, garnets, skarn, Rudnik
    ... Mining and Geology. Conditions for microanalysis were spot size 2 µm, an accele- rating voltage of 30 kV and a beam current of 10 nA, using natural and synthetic mineral standards including albite (Al, Si), wollastonite (Ca), titanium monoxide (Ti), chromium oxide (Cr), and manganese (Mn) and iron ...
    ... grossu- lar, almandine and spessartine components. REE and trace elements The REE patterns of the studied skarn garnets are norma- lized to the chondrite value of McDonough & Sun (1995) and shown in Fig. 5. Y being a pseudolanthanide was included and plotted between Dy and Ho. Different zones during ...
    ... variations in optical features and garnet chemistry are the results of their two-stage evolution. The first stage and period of garnet growth is probably buffered by mineral dissolution and reactions in the country rock. The second stage is related to hydrothermal activity when W and Fe were brought into the ...

  • Production information system of the Pljevlja coal mine

    Božo Kolonja, Ranka Stanković, Filip Vuković (2018)

  • LRMI markup of OER content within the BAEKTEL project

    Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić (2015)
    ... physical and virtual communities, where more and more are published as Open Educational Resources (OER). Nowadays, online searches for educational materials are conducted more often than a few years ago. Although Internet searches are easy and speedy, they are not always efficient and retrieve ...
    ... for terminological and linguistic support, such as query expansion, information retrieval, OER indexing, and the like. OER metadata include information such as resource title, author, subject, creation date and the like, which facilitates search, but also acquisition, use and reuse of learning ...
    ... way to add extra semantic information and extend HTML5. [12] Microdata is specified inside itemtype and itemprop attributes added to existing HTML elements; microformat keywords are added inside class attributes and RDFa relies on rel, typeof and property attributes added to existing ...

  • The effect of finite driving rate on avalanche distributions

    Sonja Radić, Sanja Janićević, Dragutin Jovković, Đorđe Spasojević (2021)
    Statistics, Probability and Uncertainty,Statistics and Probability,Statistical and Nonlinear Physics

  • Arsenic in tape waters of the south Pannonian basin (Serbia) and arsenic risk assessment

    Petar Papić, Marina Ćuk, Maja Todorović, Jana Stojković, Bojan Hajdin, Nebojša Atanacković, Dušan Polomčić (2012)
    ... this study, and consequently with higher estimated toxic and carcinogenic risk should be con- nected to the new treatment for water supply. The minimum As water gave HQ and R values of 0.29 and 0.13 per 1,000 persons, respectively, and the maximum As water resulted in HQ and R of 5.72 and 2.6 per 1,000 ...
    ... existence of toxic risk. Futhermore, in the study area the minimum As water gave HQ and R values of 0.29 and 0.13 per 1,000 persons, respectively, and the maximum As water resulted in HQ and R of 5.72 and 2.6 per 1,000 persons, and this should indicate the importance of developing a regional water sup- ply system ...
    ... Austria and Slovenia to the Carpathian Mountains in Romania. In the south, the basin is bordered by the North Dinarides in Croatia, Bosnia and Herzegovina, and Serbia, and in the north by the Tatras in Slovakia. The Danube River is also the western boundary toward Croatia, while to the north and northeast ...

  • Investigation of Co0.9Ho0.1MoO4 Nanopowders Obtained by Glycine Nitrate Procedure

    Milena Rosić, Maja Milošević, Maria Čebela, Vladimir Dodevski, Vesna Lojpur, Radomir Ljupković, Aleksandra Zarubica (2023)
    ... Technology and Metallurgy, Ss. Cyril and Methodius University in Skopje, R. N. Macedonia Iva Dimitrievska, MSc, Faculty of Technology and Metallurgy, Ss. Cyril and Methodius University in Skopje, R. N. Macedonia Marija Prosheva, MSc, Faculty of Technology and Metallurgy, Ss. Cyril and Methodius ...
    ... Sciences and Mathematics, Ss. Cyril and Methodius University in Skopje, R. N. Macedonia Prof. Dr. Viktor Stefov, Institute of Chemistry, Faculty of Natural Sciences and Mathematics, Ss. Cyril and Methodius University in Skopje, R. N. Macedonia Prof. Dr. Blazo Boev, Faculty of Natural and Technical ...
    ... Natural Sciences and Mathematics, Ss. Cyril and Methodius University in Skopje, R. Macedonia Marinela Cvetanoska, MSc, Institute of Chemistry, Faculty of Natural Sciences and Mathematics, Ss. Cyril and Methodius University in Skopje, R. Macedonia COORGANIZERS: Minstry of Education and Science of ...

  • Towards translation of educational resources using GIZA++

    Ivan Obradović, Dalibor Vorkapić, Ranka Stanković, Nikola Vulović, Miladin Kotorčević (2016)
    ... University of Belgrade, 2013. [20] D. Vitas and C. Krstev. “Construction and Exploitation of X-Serbian Bitexts”. In Cristina Vertan and Walther v. Hahn (eds.) Multilingual Processing in Eastern and Southern EU Languages: Low-Resourced Technologies and Translation, pp. 207-227, Cambridge Scholars ...
    ... of them hard to translate into and with relatively weak machine translation (MT) support. Phrase-based and syntax-based SMT models are developed to address language diversity and support the language independent nature of the methodology. For high-quality MT and to add value to existing infrastructure ...
    ... combined into a feedback vector and used to refine parallel data and retrain translation models towards a more accurate second-phase translation output. The project results will be showcased and tested on the Iversity [4] MOOC platform and on the VideoLectures.NET digital video lecture library ...

  • FrameNet Lexical Database: Presenting a Few Frames Within the Risk Domain

    Aleksandra Marković, Ranka Stanković, Natalija Tomić, Olivera Kitanović (2021)
    U radu se daje kratak prikaz teorije semantike okvira, na kojoj je zasnovana leksička baza Frejmnet. Predstavljena je koncepcija ove mreže, kao i mogućnosti njene primene. Predstavljena je i leksička analiza koja se primenjuje u projektu izrade Frejmneta i ukazano na razlike između analize zasnovane na okviru u odnosu na analizu zasnovanu na reči. Zatim je prikazano nekoliko povezanih okvira koje prizivaju reči iz domena rizika. U radu je predstavljena i platforma NLTК pomoću koje se mogu koristiti ...
    Srpski jezik, semantika okvira, FrameNet, scenario rizika, rudarski korpus, obrada prirodnog jezika
    ... cited by the following authors (Atkins 1994; Gildea and Jurafsky 2002; Atkins, Fillmore, and Johnson 2003; Prad- han et al. 2005; Boas and Dux 2017; Jurafsky and Martin 2020), gives a reliable, scientifically valid way of approaching word usage analysis and de- scription. The basis of this approach is the ...
    ... morning calm, 111–137. Fillmore, Charles J, and Beryl T Atkins. 1992. “Toward a frame-based lex- icon: The semantics of RISK and its neighbors.” Frames, fields and contrasts: New essays in semantic and lexical organization 75:102. Fillmore, Charles J, and Sue Atkins. 1994. “Starting where the Dictionaries ...
    ... are associated with. Those words are called frame-evoking words and are primarily verbs, but they also include nouns, adjectives and adverbs (Atkins, Fillmore, and Johnson 2003, 252).3 The basic units of a FrameNet analysis are frame and LU, a lexeme used in one of its senses (Fillmore et al. 2003, 297) ...

  • The use of biological markers in determination of origin and type of organic matter in the Tisza river sediments

    Snežana Štrbac, Gordana Gajica, Aleksandra Šajnović, Nebojša Vasić, Ksenija Stojanović, Branimir Jovančićević (2013)
    The objective of the study was to determine the origin and type of organic matter (OM) of the Tisza recent sediments along the distance of 153 km through the territory of Serbia. For this purpose group organic-geochemical parameters and biomarker compositions were used. All samples contain approximately same amount of OM, which was deposited under uniform, slightly reducing conditions. Based on the distribution of n-alkanes, the origin and type of OM could not be precisely estimated. However, n-alkane patterns ...
    sediments, Tisza River, organic matter, biomarkers, oil pollutants
    ... of CH2Cl2 and CH3OH and quantified. The bitumen extracts and crude oils were separated into saturated, aromatic and NSO fractions using column chromatography over silica gel. The saturated hydrocarbon fraction was eluted with n-hexane, aromatic hydrocarbons with mixture of n-hexane and dichloro- ...
    ... designate the 14α(H)17α(H) and 14β(H)17β(H) con- figurations in the steranes; αβ and βα designate the 13α(H)17β(H) and 13β(H)17α(H) configurations in the diasteranes; (S) and (R) designate con- figuration at C20 in both the steranes and diasteranes. _______________________________________________ ...
    ... compositions of terpanes and steranes and the values of the biomarker parameters in Tisza sediments, it is supposed that the oil pollution generally could be related to heavy fuel oil from tankers, due to intense river transport and, to lower extent, to crude oils from the Elemir and Rusanda oil fields ...

  • A Description of Morphological Features of Serbian: a Revision using Feature System Declaration

    Cvetana Krstev, Ranka Stanković, Vitas Duško (2010)
    In this paper we discuss some well-known morphological descriptions used in various projects and applications (most notably MULTEXT-East and Unitex) and illustrate the encountered problems on Serbian. We have spotted four groups of problems: the lack of a value for an existing category, the lack of a category, the interdependence of values and categories lacking some description, and the lack of a support for some types of categories. At the same time, various descriptions often describe exactly the same ...
    Morphology, Lexicon, lexical database, Standards for LRs
    ... category for nouns are singular and plural (shared by all involved languages), and besides that dual (for Slovene and Czech) and count (for Bulgarian). This last value in Bulgarian is similar to ‘paukal’ in Serbian which is used with small numbers two, three and four. This value, however, does not ...
    ... gender masculine, and in the same time grammatical number singular and natural number plural. Natural gender and number, instead of grammatical gender and number are used for verbal forms sastali and su. To veče, petorica(fem/sing) džentlmenovih kolega sastali(masc/pl) su(pl) se već u osam časova ...
    ... notably MULTEXT-East and Unitex) and illustrate the encountered problems on Serbian. We have spotted four groups of problems: the lack of a value for an existing category, the lack of a category, the interdependence of values and categories lacking some description, and the lack of a support for some types ...

  • Wordnet Development Using a Multifunctional Tool

    Ivan Obradović, Ranka Stanković (2007)
    In this paper we present a multifunctional tool for manipulating heterogeneous language resources. The tool handles electronic dictionaries, wordnets and aligned texts, and provides for their synchronous use in various tasks. We focus here on the description of the possibilities this tool offers in the development of wordnets. Besides the wordnet module which enables parallel handling of two wordnets, other modules, such as the module for morphological dictionaries and the module for aligned texts, as well as available finite ...
    Wordnet development, language resource integration, HLT tools
    ... regular expressions and inflectional and morphological finite state transducers (FSTs) to locate morphological, lexical and syntactic patterns, remove ambiguities, and tag simple and compound words in texts. The text parsing possibilities offered by regular expressions and FSTs proved also useful ...
    ... based on LADL format and supporting resources in Unicode has been developed in parallel, and is also available 6 . Since all three systems (Intex, Unitex, and NooJ) provide for processing of texts on basis of dictionaries, in combination with regular expressions and FSTs, and each of them has ...
    ... wordnets for Bulgarian, Greek, Romanian, Serbian and Turkish and expanding the Czech wordnet, followed an approach similar to EuroWordNet [13]. Namely, BalkaNet wordnets were also developed on basis of PWN and the top-ontology accepted in EuroWordNet, and aligned by using ILI. From a lexicographer’s ...

  • Freeze-dried nanocrystal dispersion of novel deuterated pyrazoloquinolinone ligand (DK-I-56-1): Process parameters and lyoprotectant selection through the stability study

    Jelena R. Mitrović, Maja Bjelošević Žiberna, Aleksandar Vukadinović, Daniel E. Knutson, Dishary Sharmin, Aleksandar Kremenović, Pegi Ahlin Grabnar, Odon Planinšek, Dominique Lunter, James M. Cook, Miroslav M. Savić, Snežana D. Savić (2023)
    Recently, nanocrystal dispersions have been considered as a promising formulation strategy to improve the bioavailability of the deuterated pyrazoloquinolinone ligand DK-I-56-1 (7‑methoxy-2-(4‑methoxy-d3-phenyl)-2,5-dihydro-3H-pyrazolo[4,3-c]quinolin-3-one). In the current study, the freeze-drying process (formulation and process parameters) was investigated to improve the storage stability of the previously developed formulation. Different combinations of lyoprotectant (sucrose or trehalose) and bulking agent (mannitol) were varied while formulations were freeze-dried under two conditions (primary drying at -10 or -45 °C). The obtained lyophilizates were characterized in terms ...
    Pharmaceutical Science
    ... bands at 984 and 941 m ! could indicate an open structure of the trehalose molecule, but unable to form a significant number of hydrogen bonds. For the other two samples (T+M 1 + 1 and T + M 3 + 2), the position of the bands at 989 and 931 cm'! and 986 and 932 cm ! for the first and second sample ...
    ... diameter (z-ave), polydispersity index (PDI) and redispersibiliy index (RD!) after lyophilization of nanocrystal dispersion with different sucrose/mannitol ratios (z-ave: *, ** and *** for P < 0.05, 0.01 and 0.001, respectively, PDI: +, ++ and +++ for P < 0.05, 0.01 and 0.001, respectively), Description of ...
    ... (left); with trehalose and mannitol T+M 1 + 1 (middle) and with trehalose and mannitol T+M 3 + 2 (right). The magnification was 20,000 x, scale bar 900 nm in all images. Lyophilization was performed with primary drying at -45 "C (lyophilization-2). trehalose, and mannitol) and six lyophilizates obtained ...

  • Using Lexical Resources for Irony and Sarcasm Classification

    Miljana Mladenović, Cvetana Krstev, Jelena Mitrović, Ranka Stanković (2017)
    The paper presents a language dependent model for classification of statements into ironic and non-ironic. The model uses various language resources: morphological dictionaries, sentiment lexicon, lexicon of markers and a WordNet based ontology. This approach uses various features: antonymous pairs obtained using the reasoning rules over the Serbian WordNet ontology (R), antonymous pairs in which one member has positive sentiment polarity (PPR), polarity of positive sentiment words (PSP), ordered sequence of sentiment tags (OSA), Part-of-Speech tags of words (POS) ...
    ... of ironic and non-ironic statements. In the paper [27] comparison of Naive Bayes (NB) and Decision Trees (DT) methods used to classify tweets into ironic and non-ironic, showed that the results achieved by DT method measured by the F1 measure were better (71.5% and 53.3% for the balanced and imbalanced ...
    ... used for creating features have to be changed and adjusted. To this end, a modified list of stylistic and semantic markers for a sarcasm detection has to be improved and the sen- timent lexicon has to be changed to contain hateful and offensive words and phrases. But, like in the case of irony classification ...
    ... features provide similar and low performance measures. The results of both classifiers show low grade of recall and it shows us that we should enlarge and improve lexical re- sources that have been used and expand the set of ontological rules to include procedures of generalization and specifications of con- ...

  • Serbian NER&Beyond: The Archaic and the Modern Intertwinned

    Branislava Šandrih Todorović, Cvetana Krstev, Ranka Stanković, Milica Ikonić Nešić (2021)
    U ovom radu predstavljamo srpski književni korpus koji se razvija pod okriljem COST Akcije „Distant Reading for European Literary History” CA16204. Koristeći ovaj korpus romana napisanih pre više od jednog veka, razvili smo i učinili javno dostupnim Sistem za prepoznavanje imenovanih entiteta (NER) obučen da prepozna 7 različitih tipova imenovanih entiteta, sa konvolucionom neuronskom mrežom (CNN), koja ima F1 rezultat od ≈91% na test skupu podataka. Ovaj model je dalje ocenjen na posebnom skupu podataka za evaluaciju. Završavamo poređenje ...
    ... form of finite-state transducers (Vitas and Krstev, 2012), enabled the development of a comprehensive rule-based system for NER Srp- NER. This system presented by Krstev et al. (2014) targeted 11 classes of NEs: dates and time (moments and periods), money and mea- surement expressions, geopolitical ...
    ... names (co- untries, settlements, oronyms and hydronyms), and personal names (one or more last names with or without first names and nicknames). The system was developed to recognize NEs in 1253 newspapers and similar texts. It was manually evaluated on a sample of unseen newspaper texts. The overall ...
    ... were trained and evaluated (SpaCy and Stan- ford). As a support for the developed NER models, Šandrih et al. (2019) joined several existing tools and developed various new tools, combined into a web platform NER&Beyond.2 Although NER systems in general were de- veloped mostly for newspaper and similar te- ...