Претрага

Упит dcterms_subject_txt:Lexical Representation

123 items

  • Keyword Extraction from Parallel Abstracts of Scientific Publications

    Slobodan Beliga, Olivera Kitanović, Ranka Stanković, Sanda Martinčić-Ipšić (2017)
    ... previous research [14] for terminology extraction in the Serbian language used the rule-based method for multi-word term extraction that relies on lexical resources for modeling various syntactic structures of multi-word terms. It is applied in several domains, also among them is the corpus of Serbian ...
    ... Heidelberg (2012). https://doi.org/10.1007/978-3-642-30755-3. Rehm, G., Uszkoreit, H. (Series eds.) 18. Krstev, C., Vitas, D., Stanković, R.: A lexical approach to acronyms and their definitions. In: Mariani, Z.V.J. (ed.) Proceedings of the 7th Language & Technol- ogy Conference, pp. 219–223. Fundacja ...
    ... completeness of the manuscript. 2.1 The SBKE Method The network or graph-based approach, where a network (or graph) of words is used for the representation of texts, enables the exploration of the relationships and structural information incorporated in a text very efficiently. Although, there are ...

  • Terminology Acquisition and Description Using Lexical Resources and Local Grammars

    Cvetana Krstev, Ranka Stanković, Ivan Obradović, Biljana Lazić (2015)
    Acquisition of new terminology from specific domains and its adequate description within terminological dictionaries is a complex task, especially for languages that are morphologically complex such as Serbian. In this paper we present an approach to solving this task semi-automatically on basis of lexical resources and local grammars developed for Serbian. Special attention is given to automatic inflectional class prediction for simple adjectives and nouns and the use of syntactic graphs for extraction of Multi-Word Unit (MWU) candidates for ...
    ... Acquisition and Description Using Lexical Resources and Local Grammars Cvetana Krstev, Ranka Stanković, Ivan Obradović, Biljana Lazić Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] Terminology Acquisition and Description Using Lexical Resources and Local Grammars ...
    ... access, as well as the employees' publications. - The Repository is available at: www.dr.rgf.bg.ac.rs Terminology acquisition and description using lexical resources and local grammars Cvetana Krstev Ranka Stanković Ivan Obradović Biljana Lazić University of University of University of University ...
    ... languages that are morphologi- cally complex such as Serbian. In this paper we present an approach to solving this task semi-automatically on basis of lexical re- sources and local grammars developed for Serbian. Special attention is given to auto- matic inflectional class prediction for simple adjectives ...

  • Resource-based WordNet Augmentation and Enrichment

    Ranka Stanković, Miljana Mladenović, Ivan Obradović, Marko Vitas, Cvetana Krstev (2018)
    In this paper we present an approach to support production of synsets for SerbianWordNet(SerWN)byadjustingPrincetonWordNet(PWN)synsetsusing several bilingual English-Serbian resources. PWN synset definitions were automatically translated and post-edited, if needed, while candidate literals for Serbian synsets were obtained automatically from a list of translational equivalents compiled form bilingual resources. Preliminary results obtained from a setof1248selectedPWNsynsetsshowthattheproducedSerbiansynsetscontain 4024 literals, out of which 2278 were offered by the system we present in this paper, whereas experts added the remaining 1746. Approximately one half of ...
    WordNet, bilingual resources, term alignment, parallel lists
    ... Language Technologies. Thus, for example, the Princeton WordNet - PWN (Fellbaum, 1998), has been in use for more than two decades as the standard lexical database for English. Several projects inspired by PWN for the development of wordnets for clusters of other languages have subsequently emerged, ...
    ... was followed by Matuschek and Gurevych (2013) who solved the word sense alignment (WSA) task by pairing senses with the same meaning from different lexical-semantic resources. Besides alignment with a developed wordnet, the use of other available resources for development and enrichment of wordnets have ...
    ... number of extracted synset pairs was too low, resulting in poor recall. In methods used for automatically enriching wordnets using other available lexical resources, the successfulness of the method is strongly correlated with the comprehensiveness of the resource used in the alignment process (Hristea ...

  • Properties of fly ash and slag from the power plants

    Miloš Šešlija, Aleksandra Rosić, Nebojša Radović, Milinko Vasić, Mitar Đogo, Milovan Jotić (2016)
    This paper describes the physical, chemical and mineral properties of ash and slag, which were taken from thermal power plants Nikola Tesla A, Nikola Tesla B, Kostolac A and Kostolac B. The knowledge of the mineralogical material composition is important because the type of minerals directly determines the properties of the fly ash and slag and their possible application. Laboratory tests showed that ash and slag samples consist of the following minerals: amorphous materials, quartz, feldspar, mullite, melilite, cristobalite, ...
    fly ash, slag, physical composition, chemical composition, mineral composition, X-ray diffraction method
    ... except for the coefficient of 0.60, where there is a higher amount of correlation coefficients. The histogram of slag results shows a small representation of the correlation coef- ficients untill 0.60, then small jumps appear with approximate values, while a large dispersion of correlation coefficients ...

  • 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
    ... exam- ple, for the sentence “srpski reditelj Aleksandar Saša Petrović” (Serbian director Aleksandar Saša Petrović), the corresponding triplet representation for the PERS_4 model would be: (0, 14, ”ROLE”), (16, 39, ”PERS_FULL”) where the first and the second element represent the start and the end ...

  • Integrative GHG Assessment in Oil and Gas Industry

    Aleksandar Mirković, Marija Živković, Stevan Đenadić, Darja Lubarda, Chinedu Anyanwa (2023)
    Reducing greenhouse gas emissions is one of the main targets of national strategies in European countries. As a main contributor to emissions, the energy sector is recognized as the most promising to apply measures and actions aimed to decrease GHG emissions. The Oil and Gas industry as a significant contributor to global greenhouse gas emissions is facing a growing need for estimating, mitigating, and reducing the impact of their operations on the atmosphere to stay competitive in a newly ...
    energetska tranzicija, gasovi staklene baste, industrija, nafta i gas
    ... reducing flaring: by employing the gas processing unit to utilize the gas that would otherwise bc flared. Therefore, it provides a comprehensivc representation of thc typical activities and emissions associated with the upstream sector. However, it should be noted that ecven with thesc cfforts, somc ...

  • Definition of criteria and alternatives for choosing the optimal mining method deposits when applying multi: Criteria optimization, Belgrade, June 2024

    Sanja Bajić, Dragoljub Bajić, Branko Gluščević, Radmila Gaćina, Josip Išek (2024)
    multi-criteria decision-making, definition of criteria, underground exploitation

  • Towards the semantic annotation of SR-ELEXIS corpus: Insights into Multiword Expressions and Named Entities

    Cvetana Krstev, Ranka Stanković, Aleksandra Marković, Teodora Mihajlov (2024)
    Овај рад представља активности на развоју корпуса ELEXIS-sr, српском додатку вишејезичном анотираном корпусу ELEXIS-а, који се састоји од семантичких анотација и репозиторија значења речи. ELEXIS је паралелни вишејезични анотирани корпус на десет европских језика, који може да се користи као вишејезички репер за евалуацију европских језика са мање и средње развијеним ресурсима. Фокус овог рада је на вишечланим изразима и именованим ентитетима, њиховом препознавању у скупу реченица ELEXIS-sr и поређењу са анотацијама на другим језицима. Разматрају се први кораци ...
    полилексемске језинице, именовани ентитет, вишезначност значења речи, складиште смисла, LLOD

  • Polymorphism and photoluminescence properties of K3ErSi2O7

    Predrag Dabić, Marko G. Nikolić, Sabina Kovač, Aleksandar Kremenović (2019)
    alkalni silikati elemenata retkih zemalja, silikati lantanoida, polimorfizam, fotoluminescencija, kristalna struktura

  • An Integrated Environment for Management and Exploitation of Linguistic Resources

    Ranka Stanković, Ivan Obradović (2009)
    ... queries is presented in web search, exploitation of aligned text and spatial data re- trieval. I. INTRODUCTION ARIOUS linguistic, that is, lexical and textual re- sources, are being developed within the Human Lan- guage Technology Group at the University of Belgrade (fur- ther referred ...
    ... the system of morphological dictionar- ies of Serbian (SMD). Another very important and devel- oped resource is the Serbian wordnet (SWN), a lexical data- base representing the semantic network of words in Serbian. Within this group of resources, the multilingual ontological dictionary of ...
    ... results that contain doc- uments in the alphabet used, which might not necessarily be the user’s intention. Our tools also tackle this problem. Lexical resources, such as electronic dictionaries and wordnets offer possibilities for a more systematic solving of the outlined problems related ...

  • Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian

    Ranka Stanković, Branislava Šandrih, Cvetana Krstev, Miloš Utvić, Mihailo Škorić (2020)
    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 ...
    Part-of-Speech tagging, lemmatization, corpus, evaluation, Serbian, morphological dictionary
    ... morphological dictionaries Serbian morphological dictionaries represent a rich lexical resource, which can be used in various NLP tasks (Krstev, 2008). It is being continually developed and maintained in the lexical database LeXimirka (Stanković et al., 2018), which supports different export functions ...
    ... and it generally corresponds to the traditional notion of Part- of-Speech in Serbian. These basic tags are refined by adding different markers to lexical entries. For instance, the marker +Aux differentiates auxiliary from other verbs, the marker +NProp differentiates proper nouns from other nouns ...
    ... of the Associ- ation for Computational Linguistics: Human Language Technologies, pages 271–281. Constant, M., Krstev, C., and Vitas, D. (2018). Lexical analysis of serbian with conditional random fields and large-coverage finite-state resources. In Zygmunt Vetu- lani, et al., editors, Human Language ...

  • Extraction of Bilingual Terminology Using Graphs, Dictionaries and GIZA++

    Branislava Šandrih, Ranka Stanković (2020)
    U nauci, industriji i mnogim istraživačkim oblastima, terminologija se brzo razvija. Najčešće, jezik koji je „lingua franca“ za većinu ovih oblasti je engleski. Kao posledica toga, za mnoga polja termini domena su koncipirani na engleskom, a kasnije se prevode na druge jezike. U ovom radu predstavljamo pristup za automatsko izdvajanje dvojezične terminologije za englesko-srpski jezički par koji se oslanja na usaglašeni dvojezični korpus domena, ekstraktor terminologije za ciljni jezik i alat za usklađivanje delova. Ispitujemo performanse metode na domenu ...
    ekstrakcija terminologije, validacija terminologije, GIZA++, grafovi, Unitex, klasifikacija teksta
    ... Semmar, 2018). 122 Infotheca Vol. 19, No. 2, December 2019 Scientific paper 3 Lexical Resources and Tools As previously mentioned in Section 1, the approach proposed in (Krstev et al., 2018) relies on several lexical resources and tools: i A sentence-aligned domain-specific corpus involving a source ...
    ... ical resources is not the solution due to rapid changes both in research fields and corresponding terminology. Multi-Word Expressions (MWEs) are lexical units composed of more than one word, which are syntactically, semantically, pragmatically, and/or statistically idiosyncratic (Baldwin and Kim, 2010) ...
    ... compile a bilingual aligned terminological list. This paper is organised as follows. An overview of previous work on this topic is given in Section 2. Lexical resources and tools that were used in the experiments in Subsection 3. The proposed approach is thoroughly explained in Section 4. Results and a discussion ...

  • Cutting Resistance Laboratory Testing Methodology for Underwater Coal Mining

    Vladimir Čebašek, Veljko Rupar, Stevan Đenadić, Filip Miletić (2021)
    Geology,Geotechnical Engineering and Engineering Geology
    ... thickness change, and instead of the second coal layer average depth of 50 m, a maximum depth of 60 m was employed (Figure 5). Figure 5. Schematic representation of the geological coal and gravel deposit, “Kovin”, with pressure changes with increasing depth. Minerals 2021, 11, 564 5 of 17 5. Methodology ...

  • BEYOND 2020 - Geology explorations and open pit activities affectation in reclamation designing in Kolubara Coal Mines (KCM) Serbia, new considerations

    Bojan Dimitrijević, Bogoljub Vučković, Radmila Gaćina (2023)
    Geology explorations in KCM runs from 1936. year up to these days and still ongoing. Results in >7,200 drill holes with ≈600,000 m of core drilling and gave lignite ore resources of > 4,1Bt, which 1,15Bt are excavated since 1986. of XIX up to early years of XXI century. For further mining operations in open pits stay 1,5Bt of lignite. Under waste heaps are ≈80 km2, additional 85 km2 should be filled. All of that masses/areas were, are ...

  • Production of morphological dictionaries of multi-word units using a multipurpose tool

    Ranka Stanković, Ivan Obradović, Cvetana Krstev, Duško Vitas (2011)
    The development of a comprehensive morphological dictionary of multi-word units for Serbian is a very demanding task, due to the complexity of Serbian morphology. Manual production of such a dictionary proved to be extremely time-consuming. In this paper we present a procedure that automatically produces dictionary lemmas for a given list of multi-word units. To accomplish this task the procedure relies on data in e-dictionaries of Serbian simple words, which are already well developed. We also offer an evaluation ...
    electronic dictionary, Serbian, morphology, inflection, multi-word units, noun phrases, query expansion
    ... non- compositionality and have constant references can be de- scribed using a similar approach. The NLP community offered various approaches to lexical treatment of multi-word units (MWUs) that were analyzed in detail by Savary [5]. Productive classes of MWUs, like numerals and various named entities ...
    ... LeXimir Core composed of several .Net libraries: CommonRes.dll, NlpQuery.dll, Visu- alTMX.dll and WNDictAuto.dll (Fig. 2). For communication with lexical resources LeXimir makes use of the NlpQuery.dll module. Modular organization of components provides two obvious benefits. In the first place, it ...
    ... Belgrade: Faculty of Philology, University of Belgrade, 2008. [5] A. Savary, “Computational Inflection of Multi-Word Units — A Con- trastive Study of Lexical Approaches,” Linguistic Issues in Language Technologies, vol. 1, no. 2, 2008. [6] C. Krstev and D. Vitas, “Finite State Transducers for Recognition ...

  • The application of ArcGIS for assessing the potential of solar energy in urban area: The case of Vranje

    Boban Pavlović, Milica Pešić-Georgiadis (2019)
    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 ...
    Obnovljivi izvori energije, potencijal solarne energije, GIS, mapiranje solarnog potencijala
    ... originating from each sky direction is calculated using a sun map in the same hemispherical projection as the viewshed. A sun map is a raster representation that displays the sun track or apparent position of the sun as it varies through the hours of the day and through the days of the year. The ...

  • Old or New, We Repair, Adjust and Alter (Texts)

    Cvetana Krstev, Ranka Stanković (2020)
    U ovom radu predstavljamo kako se e-rečnici i kaskade transduktora konačnih stanja implementirani u alatu Unitex mogu koristiti za rešavanje tri problema transformacije teksta: ispravljanje tekstova nakon OCR-a, vraćanje dijakritičkih znakova i prebacivanje između različitih jezičkih varijanti.
    ispravka teksta, OCR greške, restauracija dijakritika , jezičke varijante, elektronski rečnik, transduktori konačnih stanja
    ... text”, Acm Computing Surveys (CSUR) Vol. 24, no. 4 (1992): 377–439 Lazić, Biljana and Mihailo Škorić. “From DELA based Dictionary to Lex- imirka Lexical DataBase”. Infotheca – Journal for Digital Humanities Vol. 19, no. 2 (2019): 00–00, https://infoteka.bg.ac.rs/ojs/index. php/Infoteka/article/view/2019 ...
    ... be recognized correctly and had to be retyped manually. However, in this way confusing certain Cyrillic and Latin letters with similar graphical representation was avoided, e.g. a Cyrillic ‘а’ can be confused for a Latin ‘a’ (denoting the same letter) or a Cyrillic ‘р’ can be confused for a Latin ‘p’ (denoting ...

  • The ‘Umka’ landslide

    Uroš Đurić, Dragana Đurić, Miloš Marjanović, Biljana Abolmasov, Ivana Vasiljević (2024)
    We present an in-depth landslide map of the ‘Umka’ landslide near Belgrade, Serbia, at a scale of 1:5000. The map delineates elements at risk, primarily buildings and road infrastructure impacted by the landslide displacements of several cm per year, introduced during frequent reactivation stages. The Main map results from a survey of over 350 buildings and more than 7 km of state and local roads. The acquisition techniques included engineering geological field mapping, building survey, and visual interpretation of ...
    rizik od klizišta, elementi rizika, kartiranje pomoću drona, ispitivanje objekata, geotehnički monitoring

  • Atmospheric exposure vs burying: influences on damage intensity of built-in kersantite in the monument of the Small Staircase (Belgrade, Serbia)

    Nevenka Novaković, Predrag Dabić, Vesna Matović (2023)
    Proučavan je efekat „zatrpanog kamena“ na intenzitet procesa degradacije prisutnih na kersantitu koji je ugrađen u spomenik Malo stepenište. Istraživanja su vršena na uzorcima stene iz kamenoloma i na oštećenim kamenim blokovima ugrađenim u spomenik. Dok su neki delovi stepeništa bili pod zemljom 90 godina, većina kamenih elemenata je bila izložena različitim uslovima sredine i antropogenim uticajima. Urađeno je detaljno mapiranje trenutnog stanja spomenika kako bi se istražio uticaj “zatrpavanja” i kompleksne geometrije spomenika na tip propadanja i variranje ...
    Raspadanje, Indeks oštećenja, Zatrpavanje, Fizička svojstva, Kersantit

  • Electronic Dictionaries - from File System to lemon Based Lexical Database

    Ranka Stanković, Cvetana Krstev, Biljana Lazić, Mihailo Škorić (2018)
    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 ...
    ... and management, based on a central lexical data repository (lexical database). In this paper we present the model for the SMD lexical database developed following the lemon model, and the thesaurus of data categories, to be used for enabling links to other (lexical) data. The new database offers various ...
    ... migration of all 26 simple word and 15 multi-word unit Serbian dictionary files with more than 150,000 lexical entries. Keywords: lexical database, lemon, electronic dictionaries, lexical model, lexical relations 1. Introduction An application dubbed WS4LR (Krstev et al., 2006), subse- quently upgraded ...
    ... relations between lexical entries, nor cross-linking with other lexical models, such as Serbian WordNet, another important lexical resource for Serbian (Koeva et al., 2008). This was the main motiva- tion for transforming SMD dictionaries from the existing file system to a lemon based lexical database. ...