Претрага
133 items
-
Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian
The training of new tagger models for Serbian is primarily motivated by the enhancement of the existing tagset with the grammatical category of a gender. The harmonization of resources that were manually annotated within different projects over a long period of time was an important task, enabled by the development of tools that support partial automation. The supporting tools take into account different taggers and tagsets. This paper focuses on TreeTagger and spaCy taggers, and the annotation schema alignment ...... be used in different tagging environments: in a stand- alone tool, used strictly for text annotation, such as Tree- Tagger, but also in a Python module using spaCy library, which can then be used for various NLP applications. The paper is organized as follows. The resources used in this research ...
... models at once. spaCy features pre- trained models for many languages,5 which can be easily downloaded and applied. The potential of this Python module has been already rec- ognized in many applications. Authors in (Ribeiro et al., 2018) applied spaCy for parsing user-stories (i.e. short tex- tual ...Ranka Stanković, Branislava Šandrih, Cvetana Krstev, Miloš Utvić, Mihailo Škorić. "Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian" in Proceedings of the 12th Language Resources and Evaluation Conference, May Year: 2020, Marseille, France, European Language Resources Association (2020)
-
The application of ArcGIS for assessing the potential of solar energy in urban area: The case of Vranje
In order to determine the solar energy potential for a specified location, it is crucial to consider the latitude, altitude, slope, terrain morphology, atmospheric conditions, etc. Such a complex calculation and mapping of solar energy can be done using the ArcGIS geoprocessing tool, named Area Solar Radiation (ASR). By using the ASR tool, supported with the adequate input data, it is possible to calculate the maximum solar radiation energy (irradiation) for a defined area and for a specified time ...... algorithms that permit assessment of sky obstruction and reflectance etc (Dubayah R., Rich P.M., 1995). Solar Analyst Tool (SAT) is an extension module of ArcGIS, which derives a solar radiation map based on the input Digital Elevation Model (DEM) (Dubayah R., Rich P. M., 1995). Using the input ...
... PVWatts Calculator (US EPA, 2019). Based on these resources, NREL recommends these factors (US EPA, 2019): r = 15% solar panel efficiency of PV module, and PR = 86% performance ratio. [1 Tr Accepting the recommended values for and “PR”, and assuming that the solar panel area is 1 m”, the energy ...Boban Pavlović, Milica Pešić-Georgiadis. "The application of ArcGIS for assessing the potential of solar energy in urban area: The case of Vranje" in 12th International Conference on Energy and Climate Change, 9-11 October 2019, Athens - Greece, Energy Policy and Development Centre (KEPA) of the National and Kapodistrian University of Athens (2019)
-
Influence of mono- and two-component organic modifiers on determination of lipophilicity of tetradentate Schiff bases
Ispitivani su uticaji primene mono- i dvokomponentnih organskih modifikatora na određivanje lipofilnosti 12 tetradentatnih Šifovih baza metodom reverzno-fazne tankoslojne hromatografije. Osnovni cilj je da se proceni tip interakcije između posmatranih jedinjenja i komponenti primenjenih hromatografskih sistema i uspostavi neki obrazac ponašanja kako bi se lakše izabrala kombinacija organskih modifikatora koji će simulirati interakciju u biološkim sistemima na osnovu činjenica da iste osnovne intermolekularne interakcije su odgovorne za ponašanje supstanci i u biološkom i u hromatografskom sistemu. Primenjeni organski modifikator ...Nikola Stevanović, Aleksandar Mijatović, Aleksandar Lolić, Mario Zlatović, Rada Baošić. "Influence of mono- and two-component organic modifiers on determination of lipophilicity of tetradentate Schiff bases" in Chemical Papers, Springer Science and Business Media LLC (2021). https://doi.org/10.1007/s11696-021-01884-5
-
A Description of Morphological Features of Serbian: a Revision using Feature System Declaration
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 ...... allowed us to generate a reduced schemas and documentation. The new schema combines default modules: core tei, header, textstructure, with the iso-fs module which covers feature structures. 5. The Unification of Solutions As our ultimate aim is to maintain and further develop only one description ...Cvetana Krstev, Ranka Stanković, Vitas Duško. "A Description of Morphological Features of Serbian: a Revision using Feature System Declaration" in Proceedings of the 5th International Conference on Language Resources and Evaluation, LREC 2010, Valetta, Malta : European Language Resources Association (2010)
-
Model inteligentnog sistema adaptivnog upravljanja procesom prerade rude
Ivana M. Jovanović (2016-01-13)U oblasti procesa prerade rude, flotacijska koncentracija predstavlja jednu od najznačajnijih i najčešće primenjivanih metoda separacije korisnih od nekorisnih minerala. Samim tim, veoma je važno osigurati uspešan rad flotacijskog postrojenja kroz dostizanje zadovoljavajućih tehno-ekonomskih pokazatelja. Cilj upravljanja procesom flotacijske koncentracije je upravo optimizacija kvaliteta i iskorišćenja korisne komponente u koncentratu uz maksimizaciju profita. Shodno tome, istraživanja na polju modelovanja i upravljanja ovim procesom zauzimaju značajno mesto u praksi kontolnog inženjenringa.Teorijska istraživanja u okviru doktorske disertacije obuhvatila su analizu položaja ...flotacijska koncentracija, modelovanje, upravljanje, inteligentni sistem, soft kompjuting, fazi logika, veštačke neuronske mreže... principu veštačkih neuronskih mreža. Model na bazi neuronske mreže VNM1 razvijen je upotrebom programskog modula Neural Network Fitting Tool, softverskog paketa MATLAB. Ovaj programski modul koristi se za formiranje i trening neuronske mreže, kao i evaluaciju njenih performansi posredstvom srednje ...
... neuro-fazi sistem. Eksperimentalna testiranja i istraživanja pouzdanosti modela izvršena su u virtuelnom ambijentu programskog paketa MATLAB, odnosno modula Fuzzy Logic Toolbox i Neural Network Toolbox, kao i programa MS Excel. I. Jovanović, MODEL INTELIGENTNOG SISTEMA ADAPTIVNOG UPRAVLJANJA PROCESOM ...
... je protok vazduha H Ako je kvalitet N i iskorišćenje N tada je protok vazduha N b) Slika 38. Elementi kontrolne strategije: (a) Koordinacioni modul; (b) Primer fazifikacije, zaključivanja i defazifikacije u okviru fazi modela [adaptirano prema Bergh et al. (1998)]. U okviru date kontrolne ...Ivana M. Jovanović. "Model inteligentnog sistema adaptivnog upravljanja procesom prerade rude" in Универзитет у Београду, Универзитет у Београду, Рударско-геолошки факултет (2016-01-13)
-
Industrija 4.0 - koncept prediktivnog održavanja 4.0 (PdM 4.0) u rudarstvu
Četvrtu industrijsku revoluciju – Industriju 4.0 karakteriše upotreba cyber-fizičkih sistema. Da bi se postigla optimalna strategija održavanja (ali i eksploatacije), neophodno je razviti sisteme koji podržavaju napredne inteligentne sisteme održavanja ili tehnologije pametnog održavanja. Iz toga su proizašli postulati Prediktivnog održavanja 4.0 (PdM 4.0) koji definišu veoma blisku budućnost u oblasti održavanja tehničkih sistema pa i rudarske opreme. PdM 4.0 uključuje iskorišćenje snage veštačke inteligencije za stvaranje stalnog uvida u otkrivanje uzroka i anomalija u radu opreme, koje se ...Predrag Jovančić, Vesna Damnjanović, Dragan Ignjatović, Miloš Tanasijević, Stevan Đenadić. "Industrija 4.0 - koncept prediktivnog održavanja 4.0 (PdM 4.0) u rudarstvu" in IX Međunarodna konferencija UGALJ 2019, Zlatibor, Srbija, 23-26. oktobar 2019., Jugoslovenski komitet za površinsku eksploataciju (2019)
-
LRMI markup of OER content within the BAEKTEL project
... mons.org/licenses/by-nc/3.0/ Item type: http://schema.org/creativework property: datecreated: 1 September 2015 learningresourcetype: Course module name: Leksicko prepoznavanje u obradi prirodnih jezika author: Cvetana Krstev, Biljana Lazić publisher: University of Belgrade description: ...Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić. "LRMI markup of OER content within the BAEKTEL project" in The Sixth International Conference on e-Learning (eLearning-2015), September 2015, Belgrade, Serbia, Belgrade : Belgrade Metropolitan Univesity (2015)
-
Two approaches to compilation of bilingual multi-word terminology lists from lexical resources
In this paper, we present two approaches and the implemented system for bilingual terminology extraction that rely on an aligned bilingual domain corpus, a terminology extractor for a target language, and a tool for chunk alignment. The two approaches differ in the way terminology for the source language is obtained: the first relies on an existing domain terminology lexicon, while the second one uses a term extraction tool. For both approaches, four experiments were performed with two parameters being ...Branislava Šandrih, Cvetana Krstev, Ranka Stanković. "Two approaches to compilation of bilingual multi-word terminology lists from lexical resources" in Natural Language Engineering, Cambridge University Press (CUP) (2020). https://doi.org/10.1017/S1351324919000615
-
A survey of greenhouse gases production in central European lignites
Anna Pytlak, Anna Szafranek-Nakonieczna, Weronika Goraj, Izabela Śnieżyńska, Aleksandra Krążała, Artur Banach, Ivica Ristović, Mirosław Słowakiewicz, Zofia Stępniewska (2021)... T-3), respectively. Carbon content (total organic – TOC and total inorganic – IC) was determined by dry combus- tion using a TOC-VCSH with SSM-5000A module (Shimadzu, Japan). A detailed description of these analytical methods can be found at Szafranek-Nakonieczna et al. (2018). The availability of biogenic ...
... the role of the State Geological Institute. Geol. Q. 35, 207–220. Cole, J.J., Prairie, Y.T., 2014. Dissolved CO2 in freshwater systems? Reference Module in Earth Systems and Environmental Sciences. Elsevier https://doi.org/10.1016/b978- 0-12-409548-9.09399-4 DeAngelis, K.M., Allgaier, M., Chavarria ...Anna Pytlak, Anna Szafranek-Nakonieczna, Weronika Goraj, Izabela Śnieżyńska, Aleksandra Krążała, Artur Banach, Ivica Ristović, Mirosław Słowakiewicz, Zofia Stępniewska. "A survey of greenhouse gases production in central European lignites" in Science of The Total Environment, Elsevier (2021). https://doi.org/10.1016/j.scitotenv.2021.149551
-
Fuzzy Model for Risk Assessment of Machinery Failures
The main goal of this research was the development of an algorithm for the implementation of negative risk parameters in a synthesis model for a risk level assessment for a specific machine used in the mining industry. Fuzzy sets and fuzzy logic theory, in combination with statistical methods, were applied to analyze the time picture state of the observed machine. Fuzzy logic is presented through fuzzy proposition and a fuzzy composition module. Using these tools, the symmetric position of the ...... were applied to analyze the time picture state of the observed machine. Fuzzy logic is presented through fuzzy proposition and a fuzzy composition module. Using these tools, the symmetric position of the fuzzy sets with regard to class was used, and the symmetric fuzzy inference approach was used in ...
... were applied to analyze the time picture state of the observed machine. Fuzzy logic is presented through fuzzy proposition and a fuzzy composition module. Using these tools, the symmetric position of the fuzzy sets with regard to class was used, and the symmetric fuzzy inference approach was used in ...Dejan V. Petrović, Miloš Tanasijević, Saša Stojadinović, Jelena Ivaz, Pavle Stojković. "Fuzzy Model for Risk Assessment of Machinery Failures" in Symmetry, MDPI AG (2020). https://doi.org/10.3390/sym12040525
-
Keyword-Based Search on Bilingual Digital Libraries
This paper outlines the main features of Biblisha, a tool that offers various possibilities of enhancing queries submitted to large collections of aligned parallel text residing in bilingual digital library. Biblishsa supports keyword queries as an intuitive way of specifying information needs. The keyword queries initiated, in Serbian or English, can be expanded, both semantically, morphologically and in other language, using different supporting monolingual and bilingual resources. Terminological and lexical resources are of various types, such as wordnets, electronic ...Ranka Stanković, Cvetana Krstev, Duško Vitas, Nikola Vulović, Olivera Kitanović. "Keyword-Based Search on Bilingual Digital Libraries" in Semantic Keyword-Based Search on Structured Data Sources - Second COST Action IC1302 International KEYSTONE Conference, IKC 2016, Springer (2017). https://doi.org/10.1007/978-3-319-53640-8_10
-
Towards a Mining Equipment Ontology
... and for linking to the SUKU relational database, as well as for query realization, invoking store procedure and the like. Figure 4 illustrates the module for management of RudOnto within the SUKU information system. The hypernym/hyponym hierarchy tree is displayed at the left hand side of the larger ...Ranka Stanković, Ivan Obradović, Olivera Kitanović, Ljiljana Kolonja. "Towards a Mining Equipment Ontology" in Proceedings of the 12th International Conference Research and Development in Mechanical Industry, RaDMI 2012, September 2012, Vrnjačka Banja, Serbia no. 1, Vrnjačka Banja, Serbia : SaTCIP (Scientific and Technical Center for Intellectual Property) Ltd. (2012)
-
A Tool for Enhanced Search of Multilingual Digital Libraries of E-journals
This paper outlines the main features of Bibliša, a tool that offers various possibilities of enhancing queries submitted to large collections of TMX documents generated from aligned parallel articles residing in multilingual digital libraries of e-journals. The queries initiated by a simple or multiword keyword, in Serbian or English, can be expanded by Bibliša, both semantically and morphologically, using different supporting monolingual and multilingual resources, such as wordnets and electronic dictionaries. The tool operates within a complex system composed ...... pretraživač in English should be search engine. Hence, the Dictionary of librarianship should be amended accordingly. In this context, an additional module is planned, which would enable privileged users to enhance and correct the dictionaries used in query expansion on the basis of search results ...Ranka Stanković, Cvetana Krstev, Ivan Obradović, Aleksandra Trtovac, Miloš Utvić. "A Tool for Enhanced Search of Multilingual Digital Libraries of E-journals" in Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012, May 2012, Istanbul, Turkey, Istanbul, Turkey : European Language Resources Association (2012)
-
The Dictionary of the Serbian Academy: from the Text to the Lexical Database
In this paper we discuss the project of digitization of the Dictionary of the Serbo-Croatian Standard and Vernacular Language. Scanning and character recognition were a particular challenge, since various non-standard character set encoding was used in the course of the almost 60-year long production of the dictionary. The first aim of the project was to formalize the micro-structure of the dictionary articles in order to parse the digitized text of and transform it into structured data stored in relational lexical database. This approach ...... manual postediting of the digitized text. Within this research, the partial alignment of the XML tag set, defi ned for the DSA with the TEI dictionary module, was made. For instance, theelement is used to denote the grammatical gender, while refers to the terminological fi eld ... Ranka Stanković, Rada Stijović, Duško Vitas, Cvetana Krstev, Olga Sabo. "The Dictionary of the Serbian Academy: from the Text to the Lexical Database" in Proceedings of the XVIII EURALEX International Congress: Lexicography in Global Contexts, Ljubljana : Ljubljana University Press, Faculty of Arts (2018)
-
Репозиторијум дигиталних идентификатора објеката – доиФил: изградња, стање и перспективе
Милош Утвић, Михаило Шкорић (2017)Филолошки факултет Универзитета у Београду је крајем јула 2015. године склопио уговор са агенцијом Crossref и тиме стекао право да својим публикацијама додељује дигитални идентификатор објекта (DOI), као и публикацијама других издавача које заступа. Истовремено, у склопу уговора, Филолошки факултет је развио репозиторијум доиФил који за све регистроване публикације чува њихове библиографске метаподатке, хипервезу ка комплетном тексту и сам DOI. После припремних радњи и разраде процеса на којима је заснован рад репозиторијума, у новембру 2016. године је репозиторијум доиФил ...... регистровао DOI за 2100 библиографских јединица (Табела 2). Тренутно стање се може пратити на сајту репозиторијума у оквиру којег је Милош Утвић додао модул који исписује основне статистичке податке о броју регистрованих DOI-бројева18 по типовима публикација, као и индекс аутора19 који за појединачног ...Милош Утвић, Михаило Шкорић. "Репозиторијум дигиталних идентификатора објеката – доиФил: изградња, стање и перспективе" in Научна конференција Библиоинфо — 55 година од покретања наставе библиотекарства на високошколском нивоу, Београд 18. мај 2017., Филолошки факултет Универзитета у Београду (2017). https://doi.org/10.18485/biblioinfo.2017.ch7
-
Српски језик у дигиталном добу -- The Serbian Language in the Digital Age
Duško Vitas, Ljubomir Popović, Cvetana Krstev, Ivan Obradović, Gordana Pavlović-Lažetić, Mladen Stanojević (2012)... разрешавање анафора (тј. на шта се односе заменице) и референци у изразима; и представљање значења у машински читљивом олику. Након анализе текста, модули посвећени специфич- ним задацима оављају многе различите операције, каошто су аутоматскорезимирањеипрегледање аза података. Овај поједностављен и ...
... ‘*Они је исало и- смо.’Паипак, већинапрограма запроверуправописа 21 улазни текст припремна обрада граматичка анализа семантичка анализа модули за специфичне задатке излаз 6: Типична архитектура система за обраду текста неће пронаћи грешке у следећем тексту [35]: I have a spelling checker ...
... за српски језик учињени су још крајем 1970- их [36] и или су мотивисани пролемима на које су наилазиле велике издавачке куће. Данас је слоо- дан модул за проверу правописа за српски језик до- ступан за OpenOffice [37] на различитим оператив- ним системима, а постоји и занатски израђени про- извод, ...Duško Vitas, Ljubomir Popović, Cvetana Krstev, Ivan Obradović, Gordana Pavlović-Lažetić, Mladen Stanojević. "Српски језик у дигиталном добу -- The Serbian Language in the Digital Age" in META-NET White Paper Series, G. Rehm, H. Uszkoreit (eds.), Springer (2012)
-
The Reciprocal Algebraic Integers Having Small House
Dragan Stankov (2021)Algebraic integer, the house of algebraic integer, maximal modulus, reciprocal polynomial, primitive polynomial, Schinzel-Zassenhaus conjecture, Mahler measure, method of least squares, cyclotomic polynomialsDragan Stankov. "The Reciprocal Algebraic Integers Having Small House" in Experimental Mathematics (2021). https://doi.org/ 10.1080/10586458.2021.1982425
-
Keyword Extraction from Parallel Abstracts of Scientific Publications
... [25], web pages [27], etc. However, if such a keyword extraction method needs to be applicable in a bilingual or mul- tilingual environment then the module which incorporates semantic or linguistic knowledge needs to be developed for each language separately. In this paper, we test the applicability of ...Slobodan Beliga, Olivera Kitanović, Ranka Stanković, Sanda Martinčić-Ipšić . "Keyword Extraction from Parallel Abstracts of Scientific Publications" in Sematic Keyword-Based Search on Structured Data Sources - Third International KEYSTONE Conference, IKC 2017 Gdańsk, Poland, September 11–12, 2017 Revised Selected Papers and COST Action IC1302 Reports, Springer (2017)
-
From DELA Based Dictionary to Leximirka Lexical Database
Biljana Lazić, Mihailo Škorić (2020)In this paper, we will present an approach in transforming Serbian language Morphological dictionaries from a DELA text format to a lexical database dubbed Leximirka. Considering the benefits of storing data within a database when compared to storing them in textual documents, we will outline some of the functionality that the database has made possible. We will also show how hand-made rules that use category labels lexical entries are marked with can be used to link lexical entries. ...... Syntax and Semantics – synsem, De- composition – decomp, Variation and Translation – vartrans and Linguistic Metadata – lime. The most commonly used module is ontolex that describes lexical entry (morphological, semantic and ontological description). 3 Transition to lexical database 3.1 Motivation ...Biljana Lazić, Mihailo Škorić. "From DELA Based Dictionary to Leximirka Lexical Database" in Infotheca, Faculty of Philology, University of Belgrade (2020). https://doi.org/10.18485/infotheca.2019.19.2.4
-
Serbian NER&Beyond: The Archaic and the Modern Intertwinned
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 ...... tok indicates a novel’s size in terms of tokens. 4.2 Training We trained our SrpCNNER model on the SrpELTeC-gold corpus using the spaCy Pyt- hon module, version 3.0. In order to prepare the dataset for training, we first segmented texts into sentences, ending up with 43,129 sentences in total, including ...Branislava Šandrih Todorović, Cvetana Krstev, Ranka Stanković, Milica Ikonić Nešić. "Serbian NER&Beyond: The Archaic and the Modern Intertwinned" in Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Methods and Applications, INCOMA Ltd. Shoumen, BULGARIA (2021). https://doi.org/10.26615/978-954-452-072-4_141