Претрага

Упит dcterms_subject_txt:Fuzzy sets

163 items

  • A WordNet Ontology in Improving Searches of Digital Dialect Dictionary

    Miljana Mladenović, Ranka Stanković, Cvetana Krstev (2017)
    In this paper, we present a method for automatic generation of a digital resource, which connects all indirect synonyms of a dialect term to all indirect synonyms of a corresponding term in the standard language, aiming to improve the search of a digital dialect dictionary. The method uses SWRL rules defined in the Serbian WordNet ontology to identify sets of synonymous words. It also uses e-dictionaries to produce correct lemmas in standard language that users usually employ in searches. ...
    ... language aiming to improve search over a digital dialect dictionary. The method uses SWRL rules defined in the Serbian WordNet ontology to identify sets of synonymous words. It also uses e-dictionaries to produce correct lemmas in the standard language that users usually use for search. The method was ...
    ... The implementation of new search features The proposed method for connecting the standard language with the dialect dictionary relies on a table of sets of synonymous words of the standard language which are related to an equivalent set of dialect entries. This table is used as a part of the Web tool ...
    ... synonyms in the dialect by a verb in the standard language representing a set of synonyms ob- tained from SWN ontology. Next example represents two joined sets of synonyms aligned by the verb upropastitt. upropastiti unerediti, unistiti, uprskati, zabrljati, zajebati, zakrmasiti, zasvinjiti | isabim batiSem ...

  • Primena fuzzy optimizacije u hidrodinamičkoj analizi

    Dragoljub Bajić, Dušan Polomčić, Jelena Ratković, Predrag Pajić (2018)
    znanje eksperta, optimizacija, trougaoni fuzzy brojevi, upravljanje podzemnim vodama, fuzzy logika, hidrodinamički model

  • Razvoj algoritma fuzzy optimizacije u hidrodinamičkoj analizi za potrebe projektovanja sistema odbrane od podzemnih voda

    Dragoljub Bajić, Dušan Polomčić (2019)
    Sistemi za odbranu od podzemnih voda se koriste za zaštitu hidrotehničkih objekata, priobalja, meliorativnih područja, naselja, rudnika, industrijskih područja, predstavljajući značajne segmente bez kojih bi funkcionalnost ovih objekata i područja bila dovedena u pitanje. Posebno složeni sistemi odbrane od podzemnih voda se karakterišu kod ležišta mineralnih sirovina, imajući u vidu njihovu dinamičnost, koja se ogleda u stalnom širenju ležišta, kao i činjenicu da ova ležišta prodiru duboko u stensku masu različitog strukturnog tipa poroznosti, a time i u podzemne ...
    upravljanje podzemnim vodama, hidrodinamički model, fuzzy logika, trougaoni fuzzy brojevi, znanje eksperta, optimizacija

  • Creation of a Training Dataset for Question-Answering Models in Serbian

    Ranka Stanković, Jovana Rađenović, Maja Ristić, Dragan Stankov (2024)
    Razvoj i primena veštačke inteligencije u jezičkim tehnologijama značajno su napredovali poslednjih godina, posebno u domenu zadatka odgovaranja na pitanja (Question Answering - QA). Dok su postojeći resursi za QA zadatke razvijeni za glavne svetske jezike, srpski jezik je relativno zanemaren u ovoj oblasti. Ovaj rad predstavlja inicijativu za kreiranje obimnog i raznovrsnog skupa podataka za obučavanje modela za odgovaranje na pitanja na srpskom jeziku, koji će doprineti unapređenju jezičkih tehnologija za srpski jezik. Pored brojnih istraživanja o jezičkim modelima ...
    veštačka inteligencija, obrada prirodnog jezika, jezički resursi, anotirani skupovi, ekstrakcija informacija, odgovaranje na pitanja

  • 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
    ... their relations in the web of data. Moreover, it is used to make lexical data sets accessible via http(s), to publish them in accordance with W3C-standards such as RDF and SPARQL, and to provide links between lexical data sets and other LOD resources [8]. The goal of our research is to make its results ...
    ... researchers have to solve before building the automatic hate speech detection systems is finding as many as possible publicly available annotated data sets of a considerable size, especially if the system will be based on deep learning [39]. Another problem researchers face is the non-existence of generally ...
    ... agreement score κ = 0.84 among the annotators. One of the most cited papers in this field was written by Nobata et al. [25]. They worked on several data sets consisting of comments from Yahoo Finance and Yahoo News pages. They performed an annotation experiment giving the same data set to trained users and ...

  • Развој алгоритма процене ефеката ризика рада рударских машина на бази фази алгебре

    Dejan V. Petrović (2014-12-30)
    Појава изненадних отказа елемената техничких система у рударству је свакодневна појава...
    ризик, поузданост, технички систем, рударске машине, отказ, фази скупови, фази логика

  • An Approach to Efficient Processing of Multi-Word Units

    Cvetana Krstev, Ivan Obradović, Ranka Stanković, Duško Vitas (2013)
    Efficient processing of Multi-Word Units in the course of development of morphological MWU dictionaries is not easy to achieve, especially when languages with complex morphological structures are concerned, such as Serbian. Manual development of this type of dictionaries is a tedious and extremely slow process. To alleviate this problem we turned to our multipurpose software tool, dubbed LeXimir, in the production of lemmas for e-dictionaries of multi-word units. In addition to that, we developed a procedure aimed at making ...
    Natural Language Processing, Grammatical Category, Lexical Representation, MWU, multi-word unit
    ... aspx3, also known as VebRanka (previously WS4QE), which is supported by the wsQueryExpand.asm web service. The web service accepts and generates data sets in XML format, which are further converted into data structures that can be used for different purposes (string, array, table, etc.). As examples ...
    ... to Efficient Processing of Multi-Word Units 7 Fig. 2 Components of the software tool LeXimir means of appropriate FSTs. Organizing dictionaries in sets of different files is prac- tically motivated. Namely, smaller size files are much easier to manipulate. With LeXimir’s editor for MWUs the user can ...
    ... of every lemma with the function ‘Inflect’ that lists all in- flected forms of a selected lemma. Another useful function is the extraction of sub- sets of lemmas based on different criteria: lemmas’ beginning, their part of speech (PoS), inflectional class code, syntactic and/or semantic markers or ...

  • Razvoj modela upravljanja cirkulacijom u postupku bušenja korišćenjem neuro fazi sistema zaključivanja

    Seyed Ali S. Razeghi (2022)
    Gubitak isplake predstavlja nekontrolisano isticanje bušaćeg fluida kroz formacije kao što su kaverne, pukotine, ili drugi slojevi. Tradicionalne metode procene gubitka isplake se zasnivaju na primeni seizmičkih podataka ili pronalasku „mesta“ gubitka isplake na osnovu raspoloživih podataka iz susednih bušotina. Međutim, ove metode procene nisu pouzdane.‘ U disertaciji je izvršena analiza i procena uticaja parametara bušenja, geoloških faktora, karakteristika formacije i fluida na gubitak isplake kao i na formiranje fraktura u formacijama. Uspostavljeni su modeli koji podrazumevaju proces obrade ...
    naftna bušotina, gubitak isplake, fuzzy logika, ANFIS model

  • 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 ...
    ... store all forms that are inflected from a lemma, together with sets of gram- matical categories assigned. Since one lexical form can rep- resent one or more grammatical realization of a lexical en- try, it is described with one or more sets of grammatical cat- egories stored in FormGramCats. For instance ...
    ... a physical table in a database. it :ms6q (the instrumental case, singular), while two sets of grammatical codes are assigned to jezika: :ms2q and :mp2q (the genitive case, singular and plural). In addition, sets of grammatical categories are represented as individ- ual categories in the table Fo ...
    ... introduction of explicit relations between lexical entries. Besides the procedure used for mapping the existing data model to the new one, we present sets of rules developed to establish relations between lexical entries. We also present some additional improvements – automatic generation of dictionary ...

  • Extreme Rainfall Event and Its Aftermath Analysis—IPL 210 Project Progress Report

    Biljana Abolmasov, Mileva Samardžić Petrović, Ranka Stanković, Miloš Marjanović, Jelka Krušić, Uroš Đurić (2021)
    Landslides, Extreme precipitation, Data analysis, IPL project report

  • Two approaches to compilation of bilingual multi-word terminology lists from lexical resources

    Branislava Šandrih, Cvetana Krstev, Ranka Stanković (2020)
    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 ...
    Linguistics and Language,Software,Artificial Intelligence,Language and Linguistics

  • Different aspects of soft computing methods application for blasting in mining

    Katarina Urošević, Jelena Zakonović, Radmila Gaćina (2019)
    Mining is a global industry that is of great importance for every product which is used by human. For mining, process efficiency, reducing production downtime, increasing profitability are all very important. Soft computing tehnologies (SC) are helping in the process of transforming the mining industry into a safer and more environmental friendly industry, but keeping in mind the financial aspect as well. In this paper some of fields of blasting activities in which the SC methods have been applicated, ...
    soft computing, blasting, fuzzy logic, neural networks

  • Medical Domain Document Classification via Extraction of Taxonomy Concepts from MeSH Ontology

    Mihailo Škorić, Mauro Dragoni (2019)
    This paper is a result of a task that was presented to attendants of Keyword Search in Big Linked Data summer school, that was organized by Vienna University of Technology, under the Keystone COST action in the summer of 2017. It presents a specific approach to the classification via creation of minimal document surrogates based on the US National medical library’s MeSH ontology, which is derived from the Medical Subject Headings thesaurus. In a series of previously classified medically ...
    document classification, MeSH, ontology, information extraction
    ... Document classification based on their identifier vectors and a simple set of rules. 5. Evaluation of document classification performance for each of the sets used. This stage allows us to reflect on and compare different classification rules, as well as to determine whether some rulesets can (and to what ...
    ... Classification of documents using identifiers Two processing procedures were applied to the documents subject to clas- sification, resulting in two test sets. The control method was to replace the identifiers with their class, a more general hierarchical designation. The ex- perimental method also considered ...
    ... denoting a class. After applying these steps, only class identifiers now appear in document surrogates, which should be easily counted. After the test sets have been successfully created, a simple program is prepared for document classification, which requires a file with inputs in- dicating the classes ...

  • Determining seismic hazard in slowly deforming region: Can we gather enough information from karst caves?

    Ana Mladenović, Jelena Ćalić (2021)
    Methods to determine seismic hazard in any region vary depending on the regional seismicity, but can be roughly grouped into two main groups: one based on probabilistic methods that use data about known seismicity in the region, and another, which is based on data related to the faulting processes and determination of seismically active faults. Both groups of methods are relatively good for seismically active regions. However, in regions of low seismic activity and slow deformations, there is neither ...

  • 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

  • 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) ...
    ... regard we can say that ironic statement is the one where: (1) the receiver, apart from the sender, knows in advance which statement is true2 (which sets irony apart from a lie), as well as that it is opposite of the expressed statement; (2) there are stylis- tic (usage of cursive font or quotation marks) ...
    ... paper only the first six.8 Figure 2 shows an example of synsets and relations between them in the SWN ontology which are used for defining two separate sets of mutually indirect antonymous concepts. 4 IRONY CLASSIFIER Reasoning rules in the SWN ontology related to the existence of ironic pairs in which ...
    ... Lexical Resources for Irony and Sarcasm Classification Figure 3: Performance measures of the ironic/sarcastic tweets classifier depending on feature sets. not_BCMS language; after the language-dependent classifi- cation was performed, the total number of tweets that we used for further analysis was the ...

  • Concepts for Improving Machine Learning Based Landslide Assessment

    Miloš Marjanović, Mileva Samardžić Petrović, Biljana Abolmasov, Uroš Đurić (2019)
    Katastar klizišta, Podložnost, Hazard, Mašinsko učenje, Uzorkovanje, Validacija

  • Računarski integrisani sistemi za podršku odlučivanju i upravljanju u PMS, zasnovani na fuzzy logici

    Igor Miljanović (2007)
    Računarski integrisani sistemi, odlučivanje, upravljanje, PMS, fuzzy logika.

  • Determining seismic hazard in slowly deforming region: Can we gather enough information from karst caves?

    Ана Младеновић, Јелена Ћалић (2021)
    ... proper probabilistic determination of seismichazard, nor enough data about deformation that can indicate possibly active faults. Because ofthat, all sets of data have to be combined in order to gather necessary information needed todetermine seismic hazard for a given area. One of such regions of low ...

  • Pre-failure deformation monitoring as rockfall prediction tool

    Miloš Marjanović, Biljana Abolmasov, Zoran Berisavljević, Marko Pejić, Petko Vranić (2021)
    General Engineering
    ... systematic. Slope kinematic potential and joint distribution were reported in [7,8]. One set of bedding (orientation 39/44°) and two conjugated joint sets (orientation 187/62° and 148/79°) were established, appointing to the block and wedge failure potential. Rock block size and volumes (0.5-2.7 m3) ...
    ... severe activity highlighting the two top block detachments, each of about 1x1x0.5 m in size. Detachment occurs along one of the slope-forming joint sets (orientation 187/62°) that daylights locally across the slope. The tensile strength of arguably 30 MPa that holds the blocks in such daylighting setting ...
    ... within the succeeding year, and appear as a missing mass in the following sequence point cloud. Given that the slope is regularly jointed by three sets, particularly by the one which is forming the face of the cut, all exhibited displacements can be observed in X axis, instead of using total vectors ...