Претрага

Упит dcterms_subject_txt:named entity recognition

121 items

  • A Twitter Corpus and Lexicon for Abusive Speech Detection in Serbian

    Danka Jokić, Ranka Stanković, Cvetana Krstev, Branislava Šandrih (2021)
    Uvredljivi govor na društvenim medijima, uključujući psovke, pogrdni govor i govor mržnje, dostigao je nivo pandemije. Sistem koji bi bio u stanju da detektuje takve tekstove mogao bi da pomogne da internet i društveni mediji postanu bolji virtuelni prostor sa više poštovanja. Istraživanja i komercijalna primena u ovoj oblasti do sada su bili fokusirani uglavnom na engleski jezik. Ovaj rad predstavlja rad na izgradnji AbCoSER-a, prvog korpusa uvredljivog govora na srpskom jeziku. Korpus se sastoji od 6.436 ručno označenih ...
    uvredljivi jezik, govor mržnje, srpski, tviter, leksikon, korpus
    ... speech The lexicon of abusive speech, consisting of words that could be used as triggers for the recognition of abusive language is being built, with the idea that the Serbian system for the recognition and normalization of abusive expressions will also take into consideration phrases and figurative ...
    ... also established the relation with the Serbian electronic dictionaries and the management platform Leximirka (Figure 6) [22], which enables the recognition of all inflected forms of trigger words. For the ranking and selection of illustrative tweets (or its parts) as a kind of dictionary usage examples ...

  • Legal framework for recultivation of degraded areas caused by mining exploitation

    Radmila Gaćina (2023)
    Prilikom površinske i podzemne eksploatacije uglja eksploatacioni sistemi oštećuju veće ili manje površine zemljišta. Iskustva pokazuju da su oštećenja zemljišta znatno veća kod površinske eksploatacije, gde je prostora degradiran ne samo u konturi rudnika i okoline, već se promene takođe dešavaju u prirodnom okruženju. U članku su predstavljeni rezultati studije zakonskih okvira rekultivacije u nekim zemljama sveta i u Srbiji. Praktično iskustvo rekultivacije pokazalo je da iskorišćenje i devastacija tokom rudarske aktivnosti predstavljaju opasnost ne samo za pogođena ...
    rekultivacija, melioracija, otkopavanje uglja, zakonska regulativa
    ... - _ Lawon Strategic Environmental Impact Assessment, - _ Lawon Integrated Prevention and Control of Environmental Pollution. Legal and physical entity who use natural resources are obliged to keep up to date during the execution of works and performance of activities, as well as after their termination ...

  • Project BEWARE—Landslide Post-disaster Relief Activities for Local Communities in Serbia

    Biljana Abolmasov, Dobrica Damjanović, Miloš Marjanović, Ranka Stanković, Velizar Nikolić, Sandra Nedeljković, Žarko Petrović (2017)
    ... environmental, social data in analogue or digital form. Acquiring high-resolution (0.5 m) satellite images for visual and/or semi-automated landslide recognition and digitizing (interpretation) landslides. Designing field ques- tionnaires for participants’ field activities with international standards and ...
    ... efficiently and more accurately in the future. The project on harmonization of landslide data and training of municipalities for its monitoring, named BEWARE (BEyond landslide aWAREness) was designed to address these issues. The aim was to standardize post-event landslide database, closely involve ...

  • Why classical sequence stratigraphy doesn't work in Pannonian basin?

    Dejan Radivojević (2018)
    basen iza ostrvskog luka, detačment, miocen, Panonski basen, riftogeneza, sekvenciona stratigrafija
    ... In grabens with  low  subsidence, one or more of  that  systems  tract could be absent.  They are probably below seismic resolution level, so their recognition was not possible. The early rift cli‐ max systems tract usually ends up with downlap on pre‐Tertiary formations or on the initial rift systems  tract ...

  • VENTEX: An Expert System for Mine Ventilation Systems Analysis

    Ranka Stanković, Nikola Lilić, Ivan Obradović (1996)
    Analiza sistema za ventilaciju je komleksan proces, koji bazira na proračunu brojnih parametara, koji se odnose na: stanje mreže, provetrenost, stabilnost sistema, gubitke vazduha, klimatske uslove, gasno stanje, ugroženost od požara i opasne prašine. Navedeni problemi se uspešno rešavaju paketom SimVent, ali potpuno razumevanje i korišćenje dobijenih rezultata zahteva angažovanje iskusnog specijaliste iz oblasti ventilacije. Rešenje je nađeno u kreiranju ekspertnog sistema VENTEX, čija je baza znanja formalizacija ekspertskog znanja iz oblasti ventilacije rudnika. U radu je prikazana metodologija ...
    ekspertni sistem, ventilacija
    ... using a modification of the Coad- Yourdon object-oriented analysis (OOA) model (Coad and Yourdon, 1991). In the classical model every real world entity is represented by a class (object) consisting of its name, attributes and methods pertaining to the procedures related to the object. In order ...

  • Improvement of education through the cooperation between CEEPUS EURO Geo-Sci network and scientific projects: examples from UB-FMG

    Kristina Šarić, Dejan Prelević, Miloš Marjanović, Uroš Stojadinović, Vladimir Simić (2024)
    CIII-RS-0038, Recon Tethys, DEMONITOR, TMCmod, REASONING

  • Нове технологије за оживљавање старих текстова

    Цветана Крстев, Ранка Станковић, Бранислава Шандрих Тодоровић, Милица Иконић Нешић (2023)
    удаљено читање, књижевни корпус, обрада српског језика, анотација врстом речи, лематизација, именовани ентитети

  • Debris-flow Susceptibility Assessment in Flow-R: Ribnica River Case Study

    Ksenija Micić, Miloš Marjanović, Biljana Abolmasov (2024)
    Debris flows are among the most dangerous erosional geohazards due to the fast rate of movement and long runout zones. Even though the initiation can be triggered in mountainous areas, inhabited and with steep slopes, their propagation and deposition can endanger not only buildings and infrastructure in the urbanized areas, but also threaten human lives. As these initiation areas usually represent unattainable terrains with rapid vegetation cover development, field observations and aerial photo analysis become high-demanding tasks. Consequently, medium-to-regional ...
    tečenje drobine, Flow-R, procena podložnosti, empirijski model

  • Infotheca (Q25460443) in Wikidata

    Ranka Stanković, Lazar Davidović (2021)
    Vikipodaci su baza znanja Zadužbine Vikimedija koja predstavlja zajednički izvor različitih vrsta podataka koje koriste ne samo drugi Vikipedijini projekti, već sve više i brojne aplikacije semantičkog veba. U ovom radu ćemo prezentovati primer integracije Vikipodataka sa digitalnim bibliotekama i eksternim sistemima, kao i mogućnost ubrzanja pripreme i unosa podataka na primeru radova iz časopisa za digitalnu humanistiku Infoteka.
    semantički veb,otvoreni povezani podaci, vikpodaci,Infoteka, metapodaci časopisa
    ... the form of a CSV file is certainly the first step, fol- lowed by creating an OpenRefine project and loading the prepared data. What comes next is recognition of the existing Wikidata items – an indis- pensable step enabling the linking of file content to identifiers (QID) of the existing items and entry ...
    ... Nikola Tesla (Q9036) refers to the famous scientist, while Nikola Tesla (Q2732597) refers to a hous- ing project (Q486972) in Nǐska Banja (Q954986) named after him. It is rec- ommended that in the case of polysemous entities, like the above-mentioned Don Quixote (ballet) or Game of Thrones (books) an ...
    ... Open – multiple use is available under the Creative Commons CC0 li- cence granting complete freedom to use data; 3) multilingual – entities can be named and described in any natural language. These three key features are the main driving forces for the many applications, which, we believe, will inspire ...

  • WS4LR - a Worksation for Lexical Resources

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Ivan Obradović (2006)
    Lexical Resources, Wordnet, Serbian
    ... important from the practical point of view since smaller files are easier to manipulate. An even more important reason is the fact that in text recognition by Intex/Unitex the usage of all dictionaries is not always necessary, or even recommended. For example, dictionaries of English personal names ...
    ... categories of the word form, each category represented by a single character code. Morphological dictionaries of compound lemmas and word forms, named DELAC and DELACF, follow a similar format, except that both lemma and form can contain non-alphabetic characters – blank, hyphen, apostrophe, and ...

  • Primena AHP и WoEmetode u proceni podložnosti terena na kliženje za područje opštine Krupanj

    Biljana Abolmasov, Jelka Krušić, Katarina Andrejev, Miloš Marjanović, Ranka Stanković, Uroš Đurić (2017)
    ... inventory of the Republic of Serbia. Landslides, in press, DOI:10.1007/s10346-017-0847-2. [8] Fawcett T. An introduction to ROC analysis, Pattern Recognition Letters, Vol 27, pp. 861–874, 2006. [9] Fell R. et al. Guidelines for landslide susceptibility, hazard and risk zoning for land use planning, Engi- ...

  • Речник САНУ као база терминолошких речника (на примеру речника кулинарства)

    Рада Стијовић, Олга Сабо, Ранка Станковић (2017)
    ... surprise and coincidence. Computational Linguistics, 19(1), pp.61 –74. 13 5. Frantzi, K., Ananiadou, S., and Mima, H. (2000). Automatic recognition of multi-word terms:.the C-value/NC-value method. International Journal on Digital Libraries, 3(2), pp. 115-130. 6. Ranka Stanković, Cvetana ...

  • Using technology for knowledge transfer between academia and enterprises

    Ivan Obradović, Ranka Stanković (2014)
    ... valuable tool for facilitating and enhancing cooperation between different universities, on issues such as development of joint courses, or mutual recognition o diplomas. Finally, as our TEL platform is conceived as a WB-targeted OCW-based project some of its goals coincide with those of the Open consortium ...

  • The Nooj System as Module within an Integrated Language Processing Environment

    Ranka Stanković, Duško Vitas, Cvetana Krstev (2008)
    NooJ, electronic dictionary, lexical resources
    ... important from the practical point of view since smaller files are easier to manipulate. An even more important reason is the fact that in text recognition by NooJ the usage of all dictionaries is not always necessary, or even recommended. Morphological dictionaries are of great importance for highly ...
    ... and possible applications of one integrated environment for linguistic research that contains NooJ as one of its main modules. This environment named WS4LR (WorkStation for Lexical Resources) has been developed within the Human Language Technology Group (HLT) at the Faculty of Mathematics, University ...

  • Application of VIКOR method in the selection of an optimal splution of excavation “Borska Reka” ore deposit

    Sanja Bajić, Dragoljub Bajić, Branko Glušćević, Radmila Gaćina (2023)

  • Automatic construction of a morphological dictionary of multi-word units

    Cvetana Krstev, Ranka Stanković, Ivan Obradović, Duško Vitas, Miloš Utvić (2010)
    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, multiwordn units, noun phrases, query expansion
    ... Contrastive Study of Lexical Approaches. Linguistic Issues in Language Technologies 1 (2008) 4. Krstev, C., Vitas, D.: Finite State Transducers for Recognition and Generation of Compound Words. In Erjavec, T., Žganec Gros, J., eds.: IS-LTC 2006, Ljubljana, Slovenia, Institut “Jožef Stefan”(2006) 192–197 ...
    ... m.univ-mlv.fr/~unitex/. 2 Authors Suppressed Due to Excessive Length For some productive classes of MWUs, like different types of numerals and named entities (time and duration, measures and currencies), we have devel- oped finite-state transducers (FSTs) that rely on morphological e-dictionaries ...
    ... might not be such a good idea: these very dictionaries successfully processed many items, among them three very specific names of small towns in Serbia named after famous Serbian poets and politicians: Aleksa Šantić, Svetozar Miletić, Jaša Tomić. Table 6. Strategy rules performance data for subsets: ...

  • 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. ...
    Morfološki rečnici, jezički resursi, Leksimirka
    ... queries with regular expressions or FSA, their main importance is their reusability. They were used for the basic tasks of word processing, automatic recognition 1 Unitex is cross-platform Corpus Processing Suite to retrieve data. Infotheca Vol. 19, No. 2, December 2019 81 Lazić B., Škorić M., “From ...
    ... textual files. The need for an online application based on lexicographic database emerged. In response to these needs, a new application symbolically named Leximirka was developed. Leximirka is not a language dependent application and there is no obstacle for it to be applied in purpose of maintaining DELA ...
    ... started with the implementation of the Workstation for Lexical Resources WS4LR (Krstev et al., 2006). This single user desktop application later re- named Leximir has various useful functions. It is possible to distribute vo- cabularies in multiple files, extract subsets of lemmas according to various ...

  • 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
    ... not only important from the practical point of view, since smaller files are easier to manipulate, but also because of the fact that in text recognition by Intex/Unitex the usage of all dictionaries is not always necessary, or even recommended. Without going into details of dictionary management ...

  • Definition of Circulation Conditions and Groundwater Genesis of the Complex Krupaja Hydrogeological Karst System (Eastern Serbia)

    Ljiljana Vasić, Saša Milanović, Tina Dašić (2023)
    Management, Monitoring, Policy and Law,Renewable Energy, Sustainability and the Environment, Geography, Planning and Development, Building and Construction
    ... karst massif. In Proceedingss of the International Conference and Field Seminar, Karst without Boundaries (DIKTAS 2014), Trebinje, Republika Srpska Entity of Bosnia and Herzegovina, 11–15 June 2014; COBISS.RSID 4308248; pp. 73-78, ISBN 978-99938-52-58-2. Milanović, S. Physical Modeling, of Karst Environment ...

  • Digital Library From A Domain Of Criminalistics As A Foundation For A Forensic Text Analysis

    Dalibor Vorkapić, Aleksandra Tomašević, Miljana Mladenović, Ranka Stanković, Nikola Vulović (2017)
    U ovom radu predstavljen je model koji omogućava prikupljanje, pripremu, opis metapodataka, upravljanje i eksploataciju, uključujući pretragu punog teksta dokumenata iz domena kriminalistike napisanih na srpskom jeziku. Predloženi pristup primenjuje se na veb portalu koji sakuplja različite tekstove nastale iz časopisa Akademije za kriminalistiku i policijske studije, Krivičnog zakona Srbije, konferencija „Tara“ i „Reiss“, kao i iz nekih doktorskih disertacija vezanih za ovu oblast istraživanje. Nakon obrade teksta, korpus koji sadrži preko 5500 stranica običnog teksta, kreiran je i ...
    Omeka, Wordnet, pretraga punog teksta, morfološka i semantička pretraga teksta, proširenje upita
    ... morphological dictionaries, addition to terminology database, transliteration, correction of broken words, correction of optical character recognition errors. Figure 2. Use case diagrams: exploitation (left), preparation (right) APPLICATIONS FOR LINGUISTIC RESOURCES The linguistics ...