Претрага
447 items
-
Using Lexical Resources for Irony and Sarcasm Classification
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) ...Miljana Mladenović, Cvetana Krstev, Jelena Mitrović, Ranka Stanković. "Using Lexical Resources for Irony and Sarcasm Classification" in Proceedings of the 8th Balkan Conference in Informatics (BCI '17), New York, NY, USA, : ACM (2017). https://doi.org/
-
SrpCNNeL: Serbian Model for Named Entity Linking
Ovaj rad predstavlja razvoj modela za prepoznavanje i povezivanje imenovanih entiteta (NEL) sa bazom znanja Vikipodaci za srpski jezik pod nazivom SrpCNNeL. Model je obučen da prepozna i poveže sedam različitih imenovanih tipova entiteta (osobe, lokacije, organizacije, profesije, događaji, demoni i umetnička dela) na skupu podataka koji sadrži rečenice iz romana, pravnih dokumenata, kao i rečenice generisane iz znanja Vikipodataka baza i Leksimirka leksička baza podataka. Dobijeni model je pokazao dobre performanse, postigavši F1 rezultat od 0,8 na test ...Milica Ikonić Nešić, Saša Petalinkar, Ranka Stanković, Miloš Utvić, Olivera Kitanović. "SrpCNNeL: Serbian Model for Named Entity Linking" in Annals of Computer Science and Information Systems, IEEE (2024). https://doi.org/10.15439/2024F8827
-
Application of rough set theory for choosing optimal location for flotation tailings dump
Štirbanović Zoran, Miljanović Igor, Marković Zoran. "Application of rough set theory for choosing optimal location for flotation tailings dump" in Archives of Mining Sciences 58 no. 3, -:Polish Academy of Sciences - Committee of Mining (2013): 893-900. https://doi.org/10.2478/amsc-2013-0062
-
Creation of a Training Dataset for Question-Answering Models in Serbian
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 pitanjaRanka Stanković, Jovana Rađenović, Maja Ristić, Dragan Stankov. "Creation of a Training Dataset for Question-Answering Models in Serbian" in South Slavic Languages in the Digital Environment JuDig Book of Abstracts, University of Belgrade - Faculty of Philology, Serbia, November 21-23, 2024, University of Belgrade - Faculty of Philology (2024)
-
Karst aquifer average catchment area assessment through monthly water balance equation with limited meteorological data set: Application to Grza spring in Eastern Serbia
Ristić-Vakanjac Vesna, Prohaska Sevan, Polomčić Dušan, Blagojević B., Vakanjac Boris. "Karst aquifer average catchment area assessment through monthly water balance equation with limited meteorological data set: Application to Grza spring in Eastern Serbia" in Acta Carsologica, Postojina, Slovenija:Karst research institute ZRC SAZU (2013): 109-119. https://doi.org/10.3986/ac.v42i1.642
-
Modeliranje tehnoloških procesa u rudarstvu u uslovima nedovoljnosti podataka primenom teorije grubih skupova
Zoran M. Štirbanović (2015-07-01)Rudarstvo, a u okviru njega i priprema mineralnih sirovina, se odlikuje složenošću tehnoloških procesa što je posledica velikog broja uticajnih parametara. Samim tim je potrebno biti veoma obazriv prilikom donošenja odluka u oblasti rudarstva. U cilju što efikasnijeg funkcionisanja procesa, moguće je primeniti različite metode koje služe za pojednostavljenje procesa odlučivanja. Jedna od takvih metoda jeste i teorija grubih skupova. Ona predstavlja relativno novu matematičku teoriju koja je pogodna za razumevanje nepreciznih i nepotpunih podataka kao i za otkrivanje ...rudarstvo, priprema mineralnih sirovina, teorija grubih skupova, višekriterijumsko odlučivanje, flotacijsko jalovište, flotacijski kolektor, flotaciona mašinaZoran M. Štirbanović. "Modeliranje tehnoloških procesa u rudarstvu u uslovima nedovoljnosti podataka primenom teorije grubih skupova" in Универзитет у Београду, Универзитет у Београду, Рударско-геолошки факултет (2015-07-01)
-
A necessary and sufficient condition for an algebraic integer to be a Salem number
Dragan Stankov (2019)We present a necessary and sufficient condition for a root greater than unity of a monic reciprocal polynomial of an even degree at least four, with integer coefficients, to be a Salem number. This condition requires that the minimal polynomial of some power of the algebraic integer has a linear coefficient that is relatively large. We also determine the probability that an arbitrary power of a Salem number, of certain small degrees, satisfies this condition.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. "A necessary and sufficient condition for an algebraic integer to be a Salem number" in Journal de theorie des nombres de Bordeaux (2019). https://doi.org/10.5802/jtnb.1076
-
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 ...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 . "A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment" in Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), Marseille, European Language Resources Association (ELRA) (2020)
-
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 ...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)
-
Parallel Bidirectionally Pretrained Taggers as Feature Generators
In a setting where multiple automatic annotation approaches coexist and advance separately but none completely solve a specific problem, the key might be in their combination and integration. This paper outlines a scalable architecture for Part-of-Speech tagging using multiple standalone annotation systems as feature generators for a stacked classifier. It also explores automatic resource expansion via dataset augmentation and bidirectional training in order to increase the number of taggers and to maximize the impact of the composite system, which ...Ranka Stanković, Mihailo Škorić, Branislava Šandrih Todorović. "Parallel Bidirectionally Pretrained Taggers as Feature Generators" in Applied Sciences, MDPI AG (2022). https://doi.org/10.3390/app12105028
-
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 ...Ivan Obradović, Ranka Stanković. "Wordnet Development Using a Multifunctional Tool" in Proceedings of the International Workshop Computer Aided Language Processing (CALP) '2007, Borovets, Bulgaria, September 2007, - (2007)
-
The number of nonunimodular roots of a reciprocal polynomial
Dragan Stankov (2023)We introduce a sequence Pd of monic reciprocal polynomials with integer coefficients having the central coefficients fixed as well as the peripheral coefficients. We prove that the ratio of the number of nonunimodular roots of Pd to its degree d has a limit L when d tends to infinity. We show that if the coefficients of a polynomial can be arbitrarily large in modulus then L can be arbitrarily close to 0. It seems reasonable to believe that if ...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 number of nonunimodular roots of a reciprocal polynomial" in Comptes rendus mathematique, Elsevier France Editions Scientifiques et Medicales (2023). https://doi.org/10.5802/crmath.422
-
Чији је пример? Анализа лексичких обележја на примерима Речника САНУ
У овом раду поставља се питање: да ли се може утврдити ко је аутор неког текста уколико се анализирају искључиво његова лексичка обележја? Како бисмо покушали да добијемо одговор на ово питање, посматрали смо примере у оквиру речничког чланка појединачне лексеме Речника САНУ, који су забележени у пет томова (и то: I, II, XVIII, XIX и XX). Сваки пример је преузет из неког извора на шта упућују скраћенице, наведене у заградама. Од преко 5.000 понуђених извора, определили смо се ...Бранислава Б. Шандрих, Ранка М. Станковић, Мирјана С. Гочанин. "Чији је пример? Анализа лексичких обележја на примерима Речника САНУ" in Српски језик и његови ресурси, Међународни славистички центар, Филолошки факултет, Универзитет у Београду (2019). https://doi.org/10.18485/msc.2019.48.3.ch13
-
A review of Pb-Sb(As)-S, Cu(Ag)-Fe(Zn)-Sb(As)-S, Ag(Pb)-Bi(Sb)-S and Pb-Bi-S(Te) sulfosalt systems from the Boranja orefield, West Serbia
Radosavljević Slobodan, Stojanović Jovica, Pačevski Aleksandar, Radosavljević-Mihajlović Ana, Kašić Vladan (2016)Radosavljević Slobodan, Stojanović Jovica, Pačevski Aleksandar, Radosavljević-Mihajlović Ana, Kašić Vladan. "A review of Pb-Sb(As)-S, Cu(Ag)-Fe(Zn)-Sb(As)-S, Ag(Pb)-Bi(Sb)-S and Pb-Bi-S(Te) sulfosalt systems from the Boranja orefield, West Serbia" in Geološki anali Balkanskoga poluostrva 77, Beograd :Rudarsko-geološki fakultet (2016): 1-12. https://doi.org/10.2298/GABP1677001R
-
E-Connecting Balkan Languages
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.Cvetana Krstev, Ranka Stanković, Duško Vitas, Svetla Koeva. "E-Connecting Balkan Languages" in Proceedings of the Workshop Workshop on Multilingual resources, technologies and evaluation for Central and Eastern European Languages, 17 September 2009, eds. C. Vertan, S. Piperidis, E. Paskaleva and Milena Slavcheva, Borovets, Bulgaria : Association for Computational Linguistics Stroudsburg, PA, USA (2009)
-
Sentiment Analysis of Serbian Old Novels
In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: NRC, AFFIN and Bing with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into ontolex-lemon and published as initial ...Ranka Stanković, Miloš Košprdić, Milica Ikonić Nešić, Tijana Radović. "Sentiment Analysis of Serbian Old Novels" in Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data, June 2022, Marseille, France, European Language Resources Association (2022)
-
Transformer-Based Composite Language Models for Text Evaluation and Classification
Parallel natural language processing systems were previously successfully tested on the tasks of part-of-speech tagging and authorship attribution through mini-language modeling, for which they achieved significantly better results than independent methods in the cases of seven European languages. The aim of this paper is to present the advantages of using composite language models in the processing and evaluation of texts written in arbitrary highly inflective and morphology-rich natural language, particularly Serbian. A perplexity-based dataset, the main asset for the ...Mihailo Škorić, Miloš Utvić, Ranka Stanković. "Transformer-Based Composite Language Models for Text Evaluation and Classification" in Mathematics, MDPI AG (2023). https://doi.org/10.3390/math11224660
-
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 ...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)
-
The Usage of Various Lexical Resources and Tools to Improve the Performance of Web Search Engines
In this paper we present how resources and tools developed within the Human Language Technology Group at the University of Belgrade can be used for tuning queries before submitting them to a web search engine. We argue that the selection of words chosen for a query, which are of paramount importance for the quality of results obtained by the query, can be substantially improved by using various lexical resources, such as morphological dictionaries and wordnets. These dictionaries enable semantic ...LR web services, MultiWord Expressions & Collocations, Information Extraction, Information RetrievalKrstev Cvetana, Stanković Ranka, Vitas Duško, Obradović Ivan. "The Usage of Various Lexical Resources and Tools to Improve the Performance of Web Search Engines" in LREC 2008: Conference on Language Resources and Evaluation, Marrakesh, Morocco, May 2008, European Language Resources Association (ELRA) (2008)
-
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 ...Ranka Stanković, Boro Milovanović. "Part of Speech Tagging for Serbian language using Natural Language Toolkit" in 7th International Conference on Electrical, Electronic and Computing Engineering IcETRAN 2020, Academic Mind, Belgrade (2020)