Претрага

Упит dcterms_subject_txt:MultiWord Expressions

66 items

  • Advancing Sentiment Analysis in Serbian Literature: A Zero and Few-Shot Learning Approach Using the Mistral Model

    Milica Ikonić Nešić, Saša Petalinkar, Mihailo Škorić, Ranka Stanković, Biljana Rujević (2024)
    Ova studija predstavlja analizu sentimenta srpskih starih romana iz perioda 1840-1920, koristeći veliki jezički model (LLM) Mistral za tehniku učenja sa zasnovani na takozvanim "zero" i "few-shot" pokušajima. Glavni pristup uvodi inovacije osmišljavanjem istraživačkih upita (promptova) uključuju tekst sa uputstvom za klasifikaciju bez primera i na osnovu nekoliko primera, omogućavajući jezičkom modelu da klasifikuje osećanja u pozitivne, negativne ili objektivne kategorije. Ova metodologija ima za cilj da pojednostavi analizu osećanja ograničavanjem odgovora, čime se povećava preciznost ...
    zero-shot, few-shot, sentiment, Serbian, Mistral 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
    ... identifier of a data item (QID) can, in addition to being linked to a title and a description, have a number of aliases and statements (claims, expressions) representing its properties and values. A statement is an ordered triple (item, property, value), where item (Q) is any topic (person, object, place ...

  • An Efficient Class of Iterative Root-Finding Methods with Applications

    Dejan Ćebić, Nebojša Ralević (2021)

  • 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)
    Serbian language
    ... given to id- iomatic expressions and comparisons, proverbs and the like, which reflect autochthonous imagination and lin- guistic creativity. On the other hand, a large number of lexicalised expressions were created and are still be- ing created by the calquing of foreign expressions, today primarily English ...
    ... the case of coordinated clauses, the inventory of conjunctions for copulative and for adversative relations is especially rich. Relations between expressions in a text are established by various kinds of textual coordinators and textual singular paucal plural Nominative prozor prozora prozori Genitive ...
    ... of English words and expres- sions by Serbian ones is emphasised, aswell as of calqued translations from English by (authentic) Serbian words and expressions. (In a wider context, the resistance to- wards the increasing use of theLatin alphabet is also part of this resistance.) 3.4.5 Improvement of the ...

  • Towards translation of educational resources using GIZA++

    Ivan Obradović, Dalibor Vorkapić, Ranka Stanković, Nikola Vulović, Miladin Kotorčević (2016)
    ... global feature that counts the number of used phrases for all phrase tables cumulatively. Apart from machine translation, aligned words and multiword expressions can be used for searching and exploring translation variants in large parallel corpora [17]. Volk et al. argue that automatic word alignment ...

  • Phase relations and physical indicators of municipal waste from old landfills in Serbia

    Dragoslav R Rakić, Irena G Basarić Ikodinović, Jovana M Janković, Tina D Đurić (2021)
    Due to certain similarities of municipal waste and soil, usually for the determination of basic parameters of physical state, laboratory and field tests which are common in geotechnical investigations are used. It is often to construct an apparatus for special purpose to perform some specific laboratory and field tests. Therefore, different values of indicators of municipal waste physical state can be found in the literature. The basic reasons should be found in different definitions and methods that researchers use ...
    municipal waste, moisture content, unit weight, specific gravity, grain size distribution, porosityGeneral Computer Science
    ... (Gourc and Staub, 2010). Values of basic physical parameters in a certain stage of biodegradation are determined according to the following expressions: |. O ı_M H[l Ah (1—"0)F n=m An—n„—To Q) 1_Z H() w=w, — 4 G) m where: mx, mya — initial dry mass and mass of drained water ...

  • WS4LR - a Worksation for Lexical Resources

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Ivan Obradović (2006)
    Lexical Resources, Wordnet, Serbian
    ... a search key can only be a simple word lemma. We would like to enable a multi-word search as well, and to that end we plan to incorporate the multiword inflection module into WS4LR. • Inflection for the target language in aligned texts is not yet supported. Namely, the translation equivalence ...
    ... wordnets by following hypernym/hyponym relations. Synsets can be retrieved using various methods, from simple string matching to complex Xpath expressions, either predefined or specified by the user. For instance, by means of the Xpath expression “//SYNSET[DOMAIN='geology']” the user can retrieve ...

  • Fuzzy optimization in hydrodynamic analysis of groundwater control systems: Case study of the pumping station “Bezdan 1”, Serbia

    Dragoljub Bajić, Dušan Polomčić (2014)
    A groundwater control system was designed to lower the water table and allow the pumping sta-tion “Bezdan 1” to be built. Based on a hydrodynamic analysis that suggested three alternative solutions, mul-ticriteria optimization was applied to select the best alternative. The fuzzy analytic hierarchy process methodwas used, based on triangular fuzzy numbers. An assessment of the various factors that influenced the selec-tion of the best alternative, as well as fuzzy optimization calculations, yielded the “weights” of the alternativesand the ...
    groundwater lowering, groundwater management scenario, fuzzy analytic hierarchy process,expert knowledge, triangular fuzzy numbers, linguistic variables
    ... linguistic variable, with its linguistic values that make up fuzzy sets. Combinations of variables and their values produce linguistic statements (expressions), which constitute a bridge between numerical representation of informa- tion on a computer and human thinking. ZADEH (1975) introduced the “linguistic ...

  • Part of Speech Tagging for Serbian language using Natural Language Toolkit

    Ranka Stanković, Boro Milovanović (2020)
    Dok se razvijaju složeni algoritmi za NLP (obrada prirodnog jezika), osnovni zadaci kao što je označavanje ostaju veoma važni i još uvek izazovni. NLTK (Natural Language Toolkit) je moćna Python biblioteka za razvoj programa zasnovanih na NLP-u. Pokušavamo da iskoristimo ovu biblioteku za kreiranje PoS (vrsta reči) oznake za savremeni srpski jezik. Jedanaest različitih modela je kreirano korišćenjem NLTK API-ja za označavanje. Najbolji modeli se transformišu sa Brill tagerom da bi se poboljšala tačnost. Obučili smo modele na označenom ...
    obrada prirodnog jezika, mašinsko učenje, neuronske mreže
    ... significant effort. We did not invest much time in producing the rules, because we had not seen significant improvements after adding new regular expressions. TABLE IV MAPPING BETWEEN SMD_POS AND PCT_POS TAGSETS SMD_POS PCT_POS N NOM:com, NOM: col, NOM:nam, NOM:num, NOM:approx V VER, VER:aux ...

  • Selection of Artificial Lift Methods: A Brief Review and New Model Based on Fuzzy Logic

    Miroslav Crnogorac, Miloš Tanasijević, Dušan Danilović, Vesna Karović Maričić, Branko Leković (2020)
    Artificial lift methods have applications in oil wells where oil production is no longer possible due to natural reservoir energy, so this necessary energy is added by introducing lift methods. In order to achieve optimum production, the selection of an artificial lift method is very important. This paper uses fuzzy logic as a mathematical and conceptual model for selection of the optimal artificial lift method. The outcome or IF-THEN rules, as the central part of the model, is based ...
    mehaničke metode, proizvodnja nafte, fazi logika, donošenje odluka, optimizacija
    ... the observed phenomena. Regarding the number of linguistic variables, seven has been found to be the maximal number of rationally recognizable expressions that a human can simultaneously identify [18]. Therefore, the accepted value of linguistic variables for representing M performances is five (Figure ...
    ... the observed phenomena. Regarding the number of linguistic variables, seven has been found to be the maximal number of rationally recognizable expressions that a human can simultaneously identify [18]. Therefore, the accepted value of linguistic variables for representing M performances is five (Figure ...

  • Keyword-Based Search on Bilingual Digital Libraries

    Ranka Stanković, Cvetana Krstev, Duško Vitas, Nikola Vulović, Olivera Kitanović (2017)
    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 ...

  • E-Connecting Balkan Languages

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Svetla Koeva (2009)
    In this paper we present a versatile language processing tool that can be successfully used for many Balkan languages. This tool relies for its work on several sophisticated textual and lexical resources that were developed for most of Balkan languages. These resources are based on several de facto standards in natural language processing.
    Query expansion, e-dictionary, wordnet, proper name, aligned text
    ... Proceedings AILA 1990, Chalcidique, 1990. [13] E. Laporte, T. Nakamura, S. Voyatzi. A French Corpus Annotated for Multiword Nouns, in: Towards a Shared Task for Multiword Expressions (MWE 2008), in scope of the Sixth Interantional Conference on Language Resources and Evaluation (LREC'08), h ...

  • 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
    ... Further research can go towards using 9 In hindsight, a similar approach can also generate a different type of substitution based on loops or regular expressions, which would speed up replacements and reduce the effects of multiple parsings of the same document. 62 Infotheca Vol. 19, No. 1, September 2019 ...

  • A Fuzzy Expert Model for Availability Evaluation

    Dejan Ivezić, Miloš Tanasijević, Predrag Jovančić, Radiša Đurić (2019)
    Each technical system within itself carries the great potential danger of possible occurrence of failure and damages. Mining machines are characteristic by great investment values, costs of unplanned shutdowns, complex working conditions, and environment and workers hazards. Systematic monitoring of the mining machinery is of great importance for the management of the mining companies. Availability is the overall concept of quality of service. Includes information regard to operating state, an idle state, a standby state and shut down. The ...
    raspoloživost, ekspertski sistem, fazi teorija, buldozeri
    ... analyzed indicator. Regarding the number of linguistic variables, it can be found that seven is the maximal number of rationally recognizable expressions that human can simultaneously identify [8]. Therefore, the accepted value of linguistic variables is five (Fig. 2) for representing A and its ...

  • 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
    ... Slavic languages. Vintar and Fišer (2017) proposed a method to enrich the Slovenian WordNet (sloWNet) with domain-specific single and multi- word expressions. They used a large monolingual Slovene corpus of texts to extract terminology from the domain of informatics, and a parallel English-Slovene corpus ...

  • 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 ...
    ... 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 ...

  • Critical disorder and critical magnetic field of the nonequilibrium athermal random-field Ising model in thin systems

    Svetislav Mijatović, Dragutin Jovković, Sanja Janićević, Đorđe Spasojević (2019)
    Изингов модел, критично понашање, танки системи

  • The Fuzzy–AHP Synthesis Model for Energy Security Assessment of the Serbian Natural Gas Sector

    Aleksandar R. Madžarević, Dejan D. Ivezić, Miloš L. Tanasijević, Marija A. Živković (2020)
    Natural gas is used for the production of almost 20% of total energy today. The natural gas security of the Republic of Serbia is an urgent strategic, political and security issue. Serbia is one of the most vulnerable countries in Southeast Europe, because it only has one supply route. This study is a contribution to efforts to better understand the factors affecting energy security through the implementation of a new methodology based on the fuzzy–AHP synthesis model for measuring ...
    energetska bezbednost, prirodni gas, fazi AHP, AHP višekriterijumska analiza, fazi teorija
    ... linguistic values. By adding linguistic modifiers (less, more, very, very much, etc.), as well as conjunctions (and, or, not), complex linguistic expressions can be obtained. Linguistic variables can be assigned one or more linguistic values that are related to numerical values through membership and class ...
    ... , MNo, . . . , MNO}Jc, (16) for every j = o. 7. The assessment M of the observed system is finally obtained in the form that agrees with its expressions with (1) and (12): M = (MAXj=1, . . . , MAXj=n) = (µM(1), . . . , µM(j), . . . , µM(n)) (17) (V) Using expression 17, the assessment was obtained ...
    ... show the results of the classification of the partial indicators administrative applicability (A1) and indirect environment effect (E3) based on expressions 23 and 24. Table 8. Specific fuzzy values for the partial indicator administrative applicability (A1) for combined scenario 1 (SC1). LV J 0 2 ...

  • Mitigating hydrate formation in onshore gas wells: A case study on optimization techniques and prevention

    Milica Ješić, Bojan Martinović, Stefan Stančić, Miroslav Crnogorac, Dušan Danilović (2023)
    Gas wells, particularly those situated onshore, play a vital role in the global energy sector by supplying a significant portion of natural gas. However, operational challenges, notably gas hydrate formation, pose substantial issues, leading to complications such as flowline blockages and unexpected well shutdowns. Gas hydrates, crystalline structures resembling ice, ...
    Gas Well, Gas Hydrate Formation, Well Modeling, Well Performance Optimization, Choke Position Adjustments, Methanol Injection

  • A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment

    Sina Ahmadi, John P McCrae, Sanni Nimb, Fahad Khan, Monica Monachini, Bolette S Pedersen, Thierry Declerck, Tanja Wissik, Andrea Bellandi, Irene Pisani, [...] Ranka Stanković and others (2020)
    Aligning senses across resources and languages is a challenging task with beneficial applications in the field of natural language processing and electronic lexicography. In this paper, we describe our efforts in manually aligning monolingual dictionaries. The alignment is carried out at sense-level for various resources in 15 languages. Moreover, senses are annotated with possible semantic relationships such as broadness, narrowness, relatedness, and equivalence. In comparison to previous datasets for this task, this dataset covers a wide range of languages ...
    lexical semantic resources, sense alignment, lexicography, language resource
    ... lenging process as different reference keys which are used for senses, were dealt with differently. For the same reason, we did not take multi-word expressions into account in the extraction process. • Normalizing orthographies. As a historical dictionary, ODS employs an old Danish orthography. We auto- ...