Претрага

Упит dcterms_subject_txt:Text Analytics

22 items

  • Distant Reading in Digital Humanities: Case Study on the Serbian Part of the ELTeC Collection

    Ranka Stanković, Cvetana Krstev, Branislava Šandrih Todorović, Duško Vitas, Mihailo Škorić, Milica Ikonić Nešić (2022)
    In this paper we present the Serbian part of the ELTeC multilingual corpus of novels written in the time period 1840-1920. The corpus is being built in order to test various distant reading methods and tools with the aim of re-thinking the European literary history. We present the various steps that led to the production of the Serbian sub-collection: the novel selection and retrieval, text preparation, structural annotation, POS-tagging, lemmatization and named entity recognition. The Serbian sub-collection was published ...
    Corpus, Distant Reading, Digital Humanities, Linked Data, Named Entity Recognition, Text Analytics

  • SrpELTeC: A Serbian Literary Corpus for Distant Reading

    Ranka Stanković, Cvetana Krstev, Duško Vitas (2024)
    U članku je predstavljen SrpELTeC, korpus razvijen u okviru akcije COST Distant Reading for European Literary History (CA16204). Svi romani u SrpELTeC-u su odabrani, pripremljeni i obeleženi korišćenjem zajedničkih principa uspostavljenih za sve jezičke zbirke u Evropskoj zbirci književnog teksta (ELTeC). Navedeni su izazovi i rešenja u pripremi SrpELTeC od nule. Svi romani su ručno kodirani u TEI sa bogatim metapodacima i strukturnim napomenama. Automatska anotacija je uključivala POS-označavanje, lematizaciju i imenovane entitete, oslanjajući se na resurse za obradu ...
    digital humanities, Serbian literature, text corpora, distant reading , linked data, named entity recognition, text analytics

  • Knowledge and Rule-Based Diacritic Restoration in Serbian

    Cvetana Krstev, Ranka Stanković, Duško Vitas (2018)
    In this paper we present a procedure for the restoration of diacritics in Serbian texts written using the degraded Latin alphabet. The procedure relies on the comprehensive lexical resources for Serbian: the morphological electronic dictionaries, the Corpus of Contemporary Serbian and local grammars. Dictionaries are used to identify possible candidates for the restoration, while the dataobtainedfromSrpKorandlocalgrammarsassistsinmakingadecisionbetween several candidates in cases of ambiguity. The evaluation results reveal that,dependingonthetext,accuracyrangesfrom95.03%to99.36%,whilethe precision (average 98.93%) is always higher than the recall (average 94.94%).
    diacritic restoration, morphological dictionary, corpus, word n-grams, local grammars
    ... and search, various forms of query expansion can be carried out. One of the main applications of RuThes-like ontologies is text categorization and other tasks of text analytics. The mainstream technology of automatic document categorization is the machine-learning approach. This approach assumes that ...
    ... 2015). Such a basis for the text categorization makes it possible to process texts of different types and sizes: normative acts, newspaper articles, news reports, scientific publications, or sociological surveys. 5.1. Automatic Document Processing for Text Analytics The main stages of thesaurus-based ...
    ... compare the RuThes model with the WordNet-like model of knowledge representation and de- scribe some applications of RuThes-like resources for text analytics. We also consider the structure and current state of RuWordNet, WordNet-like Russian thesaurus, semi-automatically generated from RuThes data ...

  • Digitalizacija u rudarstvu: Kreiranje sistema za efikasno poslovno izveštavanje

    Stevan Đenadić, Aleksandar Mirković, Veljko Rupar (2024)
    Proces donošenja odluka u oblasti rudarstva i geologije uslovljen je blagovremenim posedovanjem kvalitetnih podataka i informacija. Kompleksnost rudarskih procesa nalaže prikupljanje podataka na dnevnom odnosno na smenskom nivou. Podaci kao takvi bez analitičkog pristupa nisu dovoljni. Kako bi pristup podacima bio brz i efikasan neophodno je posedovanje adekvatnog digitalnog rešenja uz adekvatne centralizovane baze podataka. U ovom radu je dat pregled trenutne pozicije rudarstva sa aspekta digitalne transformacije kao i predlog jednostavnog prototipa u obliku digitalnog sistema za poslovno ...
    rudarstvo, digitalna transformacija, baze podataka
    ... perspective of digital transformation, as well as a proposal for a simple prototype in the form of a digital system for business reporting and analytics. Keywords: mining, digital transformation, databases. 1. Uvod Rudarstvo i geologija podrazumevaju pronalaženje i cksploataciju ležišta korisnih ...
    ... strane menadžmenta rudarskih kompanija za implementacije rešenja koja se bave poslovnim obaveštavanjem i analitikom (engl. Business Infelligence & Analytics). Ključna uloga ovih rešenja je da, na osnovu raspoloživih podataka i primenom analitičkih procesa, pruže informacije o ključnim pokazateljima učinka ...

  • LRMI markup of OER content within the BAEKTEL project

    Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić (2015)
    ... times of day it was used, how long the learning took, how many times it was accessed etc. In BAEKTEL project paradata are gathered by Google analytics. 5. EDX ARHITECTURE For BAEKTEL project Open edX is used as a web-based platform for creating, delivering, and analyzing online courses. Figure ...
    ... Learning XML (OLX), an XML-based format for courses. Other components of edX platform are course discussions, mobile application support, analytics, but they are not related to LRMI metadata tagging. Figure 1: edX architecture (https://open.edx.org/contributing-to-edx/architecture) ...
    ... the BAEKTEL platform, machine readable information is inserted into the code of web pages, which helps search engines interpret the sense of the text on those pages, but also other metadata on OER content according to LRMI. Keywords: E-Learning, Open Educational Resources, LRMI, Microtagging ...

  • A Mathematical Learning Environment Based on Serbian Language Resources

    Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan (2018)
    In recent years, in line with ever growing usage of Information technology, the learning environments are changing. The amount of available learning materials in various forms has increased. These new environments demand comprehensive learning systems, which enable management of the learning corpus with special attention paid to relevant lexical resources. In this paper we present the concept of a Mathematical Learning Environment in Serbian (MLES), which is based on a corpus of mathematical materials and various lexical resources, enabling ...
    mathematical content, text processing, mathematical formulae
    ... indexed. User requests are also converted to LaTex, and the search proceeds as with ordinary text. Another relevant project is MathGo! that provides search and presentation of mathematical encoded text [8]. The software solution is based on the concepts of math block identification and vector ...
    ... mathematical support in solving real life problems from engineering practice. To that end complex issues had to be resolved, such as mathematical text analysis, processing of mathematical content in different formats, search of mathematical materials, indexing of mathematical content using Serbian ...
    ... outlines the structure and solutions for MLES, as well as the main features of its already developed components. Keywords: mathematical content; text processing; mathematical formulae 1. INTRODUCTION Rapid development of information technology, resulting in a growing number and availability ...

  • 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
    ... , "gender": "", "meta_ID": "", "resource_1_senses": [ { "#text": "of or relating to the spleen", "external_ID": "splenic.a.01"}, { "#text": "very irritable", "external_ID": "bristly.s.01"} ], "resource_2_senses": [ { "#text": "affected with spleen; malicious; spiteful; peevish; fretful ...
    ... Kiril Simov17, Petya Osenova17, Zara Kancheva17, Ivaylo Radev17, Ranka Stanković18, Andrej Perdih19, Dejan Gabrovšek19 *Insight Centre for Data Analytics, National University of Ireland, Galway {sina.ahmadi,john.mccrae}@insight-centre.org (other affiliations in Appendix A) Abstract Aligning senses ...
    ... Grant number DO1- 272/16.12.2019. This work is also supported by Sci- 3240 ence Foundation Ireland (SFI) under the Insight Center for Data Analytics (Grant Number SFI/12/RC/2289) and the Irish Research Council under the “Cardamom” Consolida- tor Laureate Grant (IRCLA/2017/129). 8. Bibliographical ...

  • 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
    ... novel Around the world in eighty days. This text was chosen for various reasons. First of all, the text is available in digital form for the majority of European languages, including Balkan languages. Regarding its content, it represents a suitable text for different types of analysis, especially ...
    ... Prolex database since we plan to use it in a translation environment [14]. It is our wish to work in a future with a true aligned Balkan text – that is, a text originally written in some Balkan language and translated to other Balkan languages. Figure 11. Results of a query bilingually expanded ...
    ... building models for machine translation [21]. Finally, from the practical point of view its suitability stems from the fact that it presents the sample text for the French distribution of the Unitex system [15]. Versions of the novel in fifteen languages have been acquired, but not all of these texts ...

  • Classification of Terms on a Positive-Negative Feelings Polarity Scale Based on Emoticons

    Mihailo Škorić (2017)
    The goal of this paper is to draw attention to the possibility of using emoticon-riddled text on the web in language-neutral sentiment analysis. It introduces several innovations in the existing framework of research and tests their effectiveness. It also presents a software tool especially made for that purpose, explains how it builds a database with sentimental value of terms and offers the user manual. Finally, it presents a software tool that tests the new database and gives some examples ...
    data mining, information extraction, emotions, text on the web
    ... meaning of written text, but only the grammar of the language that text is written on, which enables wider application. – Software that has a deeper understanding of the meaning of the text, often limited to one or a small number of areas. This type of software is predominantly used for text classification ...
    ... message does not contain text, and its determiner must refer to previous message. 3. if the message contains both the determiner and the text, and the following message contains determiner but not text – determiners from both messages will refer to the message that contains text. Example: A: I missed the ...
    ... g and analysis: understanding of written text and text queries, analysis of moods in the text, processing of digital linguistic resources such as automatic parallelization and automation of any operation that requires a deep understanding of the written text. – Artificial intelligence: automated co ...

  • 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
    ... research. After text processing, a corpus containing over 5500 pages of plain text is created and prepared for publication as an online resource for full text search using Omeka, an open source content management system for on line digital library development. Search capabilities, both full text and metadata ...
    ... research. The text that is not in Serbian language was removed, as well as tables, figures, references and links, as usual preparation for corpus processing. After this preparation, the text collection contained 5,500 pages of plain text, in A4 format, which was used for further text analysis and ...
    ... Forensic Text Analysis Dalibor Vorkapić, Aleksandra Tomašević, Miljana Mladenović, Ranka Stanković, Nikola Vulović Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] Digital Library From A Domain Of Criminalistics As A Foundation For A Forensic Text Analysis ...

  • A WebGIS Decision Support System for Management of Abandoned Mines

    Ranka Stanković, Nikola Vulović, Nikola Lilić, Ivan Obradović, Radule Tošović, Milica Pešić-Georgiadis (2016)
    ... offers data on usage: logins, data entry and export analytics [11]. Statistical reports provide an overview of the use of the application on the basis of log data (logons) and data entry, as well as the number of visits of the site using Google analytics. A system for reporting problems in system operation ...

  • WebGIS Cadastre of Abandoned Mines in Autonomous Province of Vojvodina

    Ranka Stanković, Nikola Vulović, Nikola Lilić, Ivan Obradović, Radule Tošović, Milica Pešić-Georgiadis (2015)
    ... overview of the use of the application on the basis of log data (logons) and data entry, as well as the number of visits of the site using Google analytics. Statistics of mining facilities and results of remote sensing by property type, by district, municipality, by mineral resource or method of ...

  • 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
    ... (for text). Table 1. Numerical data that describes the results of the term extraction system Experiment A B C I II III IV L I S -d ic t LIS-corp chunk 1 7 ,8 8 9 240,253 26,719 6,646 1,141 647 173 text 49,632 1,531 770 240 LIS-corp+ chunk 496,787 45,813 11,740 2,508 1,105 301 text 50,644 ...
    ... 644 2,500 1,075 362 E n g -T E LIS-corp chunk 3 ,1 6 9 215,317 35,226 5,063 2,233 x x text 49,632 2,233 x x LIS-corp+ chunk 446,979 44,885 8,164 3,333 x x text 50,644 3,310 x x Additional filtering of results obtained by GIZA++11 I Number of the aligned chunks after initial filtering using ...
    ... the application that imple- ments the method, are available on-line. KEYWORDS: terminology extraction, terminology validation, GIZA++, graphs, Unitex, text classification. PAPER SUBMITTED: 30 September 2019 PAPER ACCEPTED: 20 December 2019 Branislava Šandrih branislava.sandrih@fil.bg.ac.rs University ...

  • Simulation of Hydrogeological Environmental Discharge in Case of Interruption Constant Observations

    Marina Čokorilo Ilić, Dragoljub Bajić, Miroslav Popović (2024)
    Monitoring Network, data, hydrogeological environment, tunnel, simulation

  • 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
    ... Mining and Geology ranka.stankovic@rgf.bg.ac.rs Belgrade, Serbia 1 Text mending – introduction to problems Text mending is one of the simplest text transformation problems, when compared to speech recognition and generation, text summarization and machine translation. It is also one of the first problems ...
    ... character recognition (OCR) is applied. A text that fully corresponds to the original is rarely obtained since OCR is prone to errors. The quality of the resulting text depends on various factors: the software used, quality of the paper and print of the original text, and its language and alphabet. OCR software ...
    ... to a clean text.5 A text after OCR - Е. *нпjе него броћ! Тебе ће неко *еад *пптатн шта ти хоћеш, а *пгга нећеш! Него. кажи ти мени. jе ли теби *бнла позната моjа наредба, коjом се забрањуjе тумарање по турским кућама? — *Нпjе. — Jа где си ти *бно за ово месец дана — У *болннци. A text after automatic ...

  • 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) ...
    ... Enza Messina. 2015. Detecting irony and sarcasm in microblogs: The role of expressive signals and ensemble classifiers. In Data Science and Advanced Analytics (DSAA), 2015. 36678 2015. IEEE International Conference on. IEEE, 1–8. [13] Elena Filatova. 2012. Irony and Sarcasm: Corpus Generation and Analysis ...
    ... from RDF triples (?a swn:irony ?z), where a is the first and z is the last member of the observed rule. According to [1], existence of irony in a text is characterized by markers. Those are literary devices which indicate that irony is present, but if we remove them, ironic meaning does not change ...

  • Surface functional groups and degree of carbonization of selected chars from different processes and feedstock

    Marija Ilić, Franz-Hubert Haegel, Aleksandar Lolić, Zoran Nedić, Tomislav Tosti, Ivana Sredović Ignjatović, Andreas Linden, Nicolai D. Jablonowski, Heinrich Hartmann (2022)
    The knowledge ofthe structural and chemical properties of biochars is decisive for their application as technical products. For this reason, methods for the characterization of biochars that are generally applicable and allow quality control are highly desired. Several methods that have shown potential in other studies were used to investigate two activated carbons and seven biochars from different processes and feedstock. The chars were chosen to cover a wide range of chemical composition and structural properties as a hardness ...
    Biougalj, različiti procesi dobijanja, različite sirovine, površinski aktivne grupe, x-ray, FT-IR,XPS
    ... Geosciences – Plant Sciences (IBG-2), Forschungszentrum JUlich GmbH, Julich, Germany, 7 Central Institute for Engineering, Electronics and Analytics – Analytics (ZEA-3), Forschungszentrum Julich GmbH, JUlich, Germany • These authors contributed equally to this work. + These authors also contributed ...
    ... S2 Fig in S1 File. The scattering angles are given as values of 20 and for better comparison with some literature also as distances in A in the text. Qtz pj OR AAA || AC2 Qtz SW500f OO Cal HW500f Cal BW550s Cal ~ HW1100g Cal PW700g Alb CS180h M200h 20 30 40 50 60 70 80 ...

  • A Model for Determining the Dependability of Continuous Subsystems in Coal Mines Using the Fuzzy Logic Approach

    Nikola Stanić, Miljan Gomilanović, Petar Marković, Daniel Krzanović, Aleksandar Doderović, Saša Stepanović (2024)
    This study presents a unique model for assessing the dependability of continuous parts of combined systems in open-pit mining through the application of fuzzy logic. Continuous sub-systems as part of the combined system of coal exploitation in surface mines have the basic function of ensuring safe operation, high capacity with high reliability, and low costs. These subsystems are usually part of the thermal power plant’s coal supply system and ensure stable fuel supply. The model integrates various independent partial ...
    fuzzy logic, max-min composition, continuous part of combined system (CCS), open pit, mining, dependability

  • Sistem poslovne inteligencije za upravljanje zaštitom na radu u rudarskoj industriji

    Ljiljana R. Kolonja (2016-09-23)
    Postojeća organizacija zaštite na radu na površinskim kopovima uglja često nije umogućnosti da blagovremeno i tačno ukaže na nedostatke, koji mogu u bližoj ilidaljoj budućnosti da budu uzrok narušavanja bezbednosti radnika, ali i uzrokoštećenja materijalnih dobara rudnika. Nemogućnost donošenja pravovremenihodluka je moguće izbeći uvođenjem softverski podržanih sistema za praćenje ianalizu bezbednosti i zaštite na radu.Osnovni cilj ove doktorske disertacije je definisanje metodologije i razvoj modelasistema upravljanja zaštitom na radu, koji će omogućiti savremen, adekvatan isveobuhvatan način praćenja i analize ...
    rudarstvo, bezbednost i zdravlje na radu, poslovna inteligencija,tehnička zaštita, ontologije
    ... intelligence technology. Communications of the ACM, 54, 88‐98. CHEN, H., CHIANG, R. H. L. & STOREY, V. C. 2012. Business Intelligence and Analytics: From Big Data to Big Impact. MIS quarterly, 36, 1165‐1188. CHENG, H., LU, Y.‐C. & SHEU, C. 2009. An ontology‐based business intelligence ...

  • Ontološki model upravljanja rizikom u rudarstvu

    Olivera Kitanović (2021)
    Rudarska proizvodnja obuhvata kompleksne tehnološke sisteme, što nameće potrebu za uspostavljanjem i unapređivanjem sistema upravljanja rizikom. Heterogenost i obim podataka neophodnih za upravljanje rizikom zahtevaju sistem koji ih na fleksibilan način integriše i omogućava njihovo optimalno korišćenje. Osnovni cilj ove disertacije je razvoj ontologije za domen rudarstva i na njoj zasnovanog modela za upravljanje rizikom. Njegova realizacija podrazumeva i implementaciju algoritama ekstrakcije informacija za popunjavanje ontologije, kao i odgovarajuće softversko rešenje. Razvoj modela obuhvata i značajno proširenje rudarskog korpusa, kao ...
    rudarstvo, rizik, upravljanje rizikom, procena rizika, ontologija, semantička mreža, ekstrakcija informacija, upravljanje znanjem, računarska lingvistika
    ... ” In The Balancing Act: Combining Symbolic and Statistical Approaches to Language. Dasgupta, Tirthankar, and Lipika Dey. 2016. “Enterprise Risk Analytics: Automatic Analysis of Risk Factors from Textual Feedbacks.” In 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 001735–40 ...
    ... Proactive Risk Management Based On The Text Mining Classification.” International Journal of Engineering Research and Technology 1. Roller, Stephen, Douwe Kiela, and Maximilian Nickel. 2018. “Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora.” ArXiv Preprint ArXiv:1806.03191 ...
    ... Symposium: Exploring Attitude and Affect in Text: Theories and Applications, Stanford, CA. Ružin, Tatjana Ž. 2015. “Glagoli Uzrokovanja u Engleskom i Srpskom Jeziku.” PhD Thesis, Univerzitet u Beogradu-Filološki fakultet. Salton, Gerard. 1989. “Automatic Text Processing: The Transformation, Analysis, ...