Претрага

Упит dcterms_subject_txt:text on the web

2529 items

  • 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 ...
    ... explain how we have turned the SrpELTeC corpus into a dataset for NER. Afterwards, we describe the training of the NER model SrpCNNER, followed by a detailed evaluation. Web users can naviga- te to http://ner.jerteh.rs/ in order to apply the SrpCNNER model directly on input text. The model can also be applied ...
    ... SrpELTeC-gold novels. The first four digits of text identifiers represent the year of the first publication of a novel. For some novels, NER was not performed on the whole text, but rather on randomly selected chapters. These annotated samples were also included in the gold standard. The cumulative values ...
    ... provide choice to annotators. The fundamental difference was the input format these platforms needed: BRAT tool uses the standoff format, whilst INCEpTION relies on the CoNLL-2002 verticalized format.11 In order to convert from one format into another, we used the NER&Beyond web application. Table 2 displays ...

  • 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
    ... of the tool on basis of user feedback. Such enhancements include specific search mechanisms and mechanisms for extraction of groups of synsets on basis of various criteria. The HLT group is now working on porting the most important functions of WS4LR on the web. The ambition of the HLT group ...
    ... full-scale web version of this tool which would, among other things, enable its usage in wordnet development by several lexicographers concurrently, with all the possibilities the desktop version now offers. Presently, some of the WS4LR functions are available on the web for searches based on mo ...
    ... Namely, Intex did not support the processing of texts in Unicode, and as the usage of this encoding became more and more frequent, the development of a new tool that could handle text in Unicode became inevitable. Building on the functionalities of Intex, but allowing the processing of texts in ...

  • 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
    ... 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 ...
    ... pp. 61–80 the source text the text with suggested corrections KGB mu je ponudio da sarad- juje s njima, i da ce mu onda knjige biti objavljivane. Brod- ski je odbio. I nije mogao da objavljuje. Posle nekog vre- mena predlozili su mu da na- pusti zemlju, i da ce tako biti najbolje, za njega i za drzavu ...
    ... of finite-states transducers – in these cascades each FST works on a texts produced by a FST that directly precedes it 76 Infotheca Vol. 19, No. 2, December 2019 Scientific paper Ijekavian ⇒ Ekavian the source text the output text "Na Medicinskom fakultetu u Foči ove godine u planu je multid ...

  • Multi-word Expressions for Abusive Speech Detection in Serbian

    Ranka Stanković, Jelena Mitrović, Danka Jokić, Cvetana Krstev (2020)
    Ovaj rad predstavlja istraživanja na usavršavanju i unapređenju srpske verzije rečnika Hurtlex, višejezičnog leksikona uvredljivih reči. Posebnu pažnju posvećujemo dodavanju izraza sa više reči (polileksemskih jedinica) koji se mogu smatrati uvredljivim, jer su takvi leksički zapisi veoma važni za postizanje dobrih rezultata u mnoštvu zadataka otkrivanja uvredljivog jezika. Srpski morfološki rečnici se koriste kao osnova za čišćenje podataka i stvaranje rečnika. Istaknuta je veza sa drugim leksičkim i semantičkim resursima na srpskom jeziku i predviđena je izgradnja sistema za ...
    uvredljiv govor, govor mržnje, leksički izvori, višejezični leksikon, izrazi sa više reči
    ... applying rules for classification of offensive content, the authors may decide to classify the text in a certain category based on the number of abusive expressions above a certain threshold, e.g. if 2 or more notions of high abusiveness are found in text, it is marked as very abusive (Gitari et al., 2015; ...
    ... classifiers for recognizing abusive speech in text using the lexicon content as the training set (Wiegand et al., 2018). On the other hand, high quality corpora of hate speech, offensive speech, and abusive language are just as important for tackling the detection of these phenomena online (Zampieri ...
    ... intolerance. The aim was to develop a system which would recognize the news covering these topics, annotating certain components of the text, which, viewed individually or together, indicate the required information. The authors conclude that further development of the system could go in the direction of ...

  • Open Educational Resources in Serbia

    Ivan Obradović, Ranka Stanković, Marija Blagojević, Danijela Milošević (2020)
    Open educational resources, BAEKTEL, Metadata portal
    ... ● Terminological web application for management, browse and search of terminological resources. ● Web services for linguistic support (query expansion, information retrieval, OER indexing, etc) ● Annotation of selected resources ● OER repository on local edX platform. The BAEKTEL OER framework ...
    ... tasks, and the like. The Open Education Initiative Portal features 14 OERs selected from other portals, that are evaluated as good quality and might be interesting for a wider audience. Apart from several OERs related to programming and web design, it includes learning materials on Social Networks ...
    ... user modeling and Semantic Web. She teaches traditional, online and blended IT courses. She was coordinator of the regional Tempus project DL@WEB for improving the quality of distance learning in higher education institutions in the Western Balkans and responsible for the development of accreditation ...

  • 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

  • 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
    ... mathematics were compiled from various on-line resources and textbooks and used for generating lists of translational equivalents. Finally, we compiled a list of aligned en-sr terms from the web site of the Serbian Institute for Standardization. 3. Production The final parallel list of translation ...
    ... is a scripting language based on JavaScript that provides easy ways to automate tasks across Google products and third party services and build web applications – https://developers.google.com/apps-script/overview 3https://cloud.google.com/translate/docs/translating-text Proceedings of CLIB 2018 106 ...
    ... extract terminology from the domain of informatics, and a parallel English-Slovene corpus and an online dictionary as bilingual resources to facilitate the addition of new terms to sloWNet, based on the semantic structure of the PWN. The Croatian Wordnet (CroWN) was enlarged with the WN-Toolkit and CroDeriV ...

  • Effects of dissolution of mantle orthopyroxene on crystallization of cognate clinopyroxene: evidence from study of Serbian Paleogene xenolith-bearing alkaline rocks

    Radivojević Maša, Cvetković Vladica, Erić Suzana, Šarić Kristina (2012)

  • Development of A Business Intelligence Tool For Accident Analysis in Mines

    Ljiljana Kolonja, Ranka Stanković, Ivan Obradović, Olivera Kitanović, Uroš Pantelić (2015)
    ... machine, etc. The approach to mine safety knowledge codification in RudOnto was mainly based on the Taxonomy for Indexing Web-Based Mining Safety and Health Research (Glowacki, 2008) developed at the U.S. National Institute for Occupational Safety and Health’s (NIOSH), which is the leading world ...
    ... year. For the second cube, the measures taken into consideration are the type of injury, the day in the week on which it happened and the age of the injured worker. Based on the first cube we can conclude that the number of injuries in the year 2011 was way over the average, and that the greatest ...
    ... an effective manner (Dhillon, 2003). The BI system for support of decision making in safety management uses a combination of various information technologies, such as OLTP (On Line Transactional Processing), OLAP (On Line Analytical Processing), WEB, SQL Server Reporting Services, etc. Hence ...

  • Razvoj ARCGIS geobaze površinskog kopa korišćenjem UML CASE alata

    Aleksandra Tomašević, Ljiljana Kolonja, Ivan Obradović, Ranka Stanković, Olivera Kitanović (2012)
    ... servers, on the web or mobile devices used in the field. The GIS development platform used for the project outlined in this paper, but also for many other GIS projects developed at the University of Belgrade, Faculty of Mining and Geology, is precisely the software package ArcGIS. GEODATABASE MODELING ...
    ... extension. In the era of web publication of data in all areas, we plan to create a web GIS portal with contents from the OpmGIS database. ACKNOWLEDGMENTS This paper has been realized in the scope of the project “Improving the technology of open pit exploitation of lignite with the goal of enhancing ...
    ... by direct import in ArcMap. Figure 6 depicts the development environment of the OpmGIS base with the content of several thematic layers shown on the left side of the panel, and an overlapped visual representation on the right. The background of the map is set to a spatially referenced orthophoto ...

  • Multiword Expressions between the Corpus and the Lexicon: Universality, Idiosyncrasy and the Lexicon-Corpus Interface

    Verginica Barbu Mititelu, Voula Giouli, Kilian Evang, Daniel Zeman, Petya Osenova, Carole Tiberius, Simon Krek, Stella Markantonatou, Ivelina Stoyanova, Ranka Stankovic, Christian Chiarcos (2024)
    Predstavljamo trenutne aktivnosti na definisanju interfejsa leksikona i korpusa koji će služiti kao referenca u prikazu polileksemskih jedinica - višečlanih izraza - (različitih tipova - imenskih, glagolskih, itd.) u specijalizovanim leksikonima i povezivanju ovih unosa sa njihovim pojavljivanjima u korpusima. Konačni cilj je korišćenje ovakvih resursa za automatsko identifikovanje višečlanih izraza u tekstu. Uključivanje nekoliko prirodnih jezika ima za cilj univerzalnost rešenja koje nije usredsređeno na određeni jezik, kao i prilagođavanje idiosinkrazijama. Raspravljaju se izazovi u leksikografskom opisu višerečnih ...
    multiword expression lexicon, corpus, proof-of-concept lexicon encoding

  • SASA Dictionary as the Gold Standard for Good Dictionary Examples for Serbian

    Ranka Stanković, Branislava Šandrih, Rada Stijović, Cvetana Krstev, Duško Vitas, Aleksandra Marković (2019)
    У овом раду представљамо модел за избор добрих примера за речник српског језика и развој иницијалних компоненти модела. Метода која се користи заснива се на детаљној анализи различитих лексичких и синтактичких карактеристика у корпусу састављених од примера из пет дигитализованих свезака речника САНУ. Почетни скуп функција био је инспирисан сличним приступом и за друге језике. Дистрибуција карактеристика примера из овог корпуса упоређује се са карактеристиком дистрибуције узорака реченица ексцерпираних из корпуса који садрже различите текстове. Анализа је показала да ...
    Српски, добри примери из речника, аутоматизација израде речника, издвајање својстава, Машинско учење
    ... dependent on the headword, e.g. its position in the example. They were classified as headword dependent and will be part of future analysis. 3.3 API for feature extraction The extraction of features is implemented as a web service7. This web service is also used for other tasks, such as text classification ...
    ... into the web application and selections of parameters and features to be calculated will be enabled. Full system integration will combine the use of a lexical database with corpora exploitation via the developed web service and software. Since the work on digitization of other volumes of the SASA ...
    ... extraction Feature extraction is enabled by the development of a web service inspired by the work described in Kilgarriff et al. (2008), Kosem (2017), and Kosem et al. (2019), which can presently extract 41 features. The developed service receives a text snippet as a string (in our case a sentence) ...

  • OER obrazovni sadržaji kao spona između akademskog i preduzetničkog znanja

    Ivan Obradović, Ranka Stanković, Marija Radojičić (2014)
    ... l Resources(OER). In: theCommonwealth of Learning, 2011. [2] C.J. Bonk. The world is open: How web technology is revolutionizing education,Wiley, 2009. [3] D. Millard, K. Borthwhick, Y. Howard, P. McSweeny, C. Hargood. The HumBox:Changing educational practice around a learning resource repository ...
    ... računarskih veština. Sam postupak kreiranja kursa je relativno jednostavan, a postoji i on line podrška u vidu tutorijala. Da bi korisnik kreirao edX kurs u okviru BAEKTEL projekta neophodno je da pristupi web adresi: http://edx.baektel.eu:18010, gde će se registrovati i prijaviti za kreiranje kurseva ...
    ... Association for the Advancement of Science,2015. Retrieved from:http://www.jstor.org/stable/20177128 [10] A. Bissell. Permission granted: Open licensing for educational resources. Open Learning.The Journal of Open, Distance, and e-Learning24(1), 2009, 97–106. [11] A.J.Jacobs.Two cheers for Web U! New York ...

  • An Italian-Serbian Sentence Aligned Parallel Literary Corpus

    Saša Moderc, Ranka Stanković, Aleksandra Tomašević, Mihailo Škorić (2023)
    This article presents the construction and relevance of an Italian-Serbian sentence-aligned parallel corpus, delving into the aligned sentences in order to facilitate effective translation between the two languages. The parallel corpus serves as a valuable resource for language experts, researchers, and language enthusiasts, fostering a deeper understanding of linguistic nuances and cultural expressions. By bridging the gap between Serbian and Italian, this corpus opens new avenues for cross-cultural communication and collaboration, and ultimately contributes to the improvement of language-related ...
    Aligned corpus, parallel corpus, Serbian, Italian, literature

  • Речници у дигиталном добу - информатичка подршка за српски језик

    Биљана Рујевић (2022)
    Морфолошки речници српског језика представљају електронски језички ресурс који има значајну историју развоја и коришћења за потребе обраде природних језика. С обзиром на то да су чувани у облику датотека чији је број нарастао па је самим тим управљање речницима постало отежано јавила се потреба за смештањем информација из речника у облик лексикографске базе. Како би се омогућио симултани рад на развоју речника за више корисника јавила се потреба за веб-апликацијом заснованој на лексикографској бази. Како би се размотриле ...
    електронски речници, лексикографска база података, лексички ресурси, српски језик

  • Претрага корпуса заснована на употреби екстерних лексичких ресурса путем веб-сервиса

    Милош Утвић, Ранка Станковић, Александра Томашевић, Михаило Шкорић, Биљана Лазић (2019)
    У раду се разматра хибридни приступ претрази корпуса, илустрован на примеру алатки OCWB и NoSketch Engine, примењених на специјални корпус из области рударства (РудКор) и Корпус савременог српског језика (СрпКор). Разматрани приступ комбинује постојеће могућности алатки OCWB и NoSketch Engine, које своју претрагу заснивају на лингвистичкој анотацији корпуса, са новим могућностима претраге у виду консултовања екстерних језичких ресурса (морфолошки електронски речници српског језика и лексичка база података Српски ворднет). Хибридни приступ је реализован надоградњом вебсучеља која поменуте алатке користе ...
    корпус, рударство, претраживање информација, проширивање упита, лексички ресурси, лексичке релације
    ... Contemporary Serbian (SrpKor). The discussed approach combines existing functionality of tools OCWB and NoSketch Engine (a search based on embedded linguistic annotation of corpus) with newly implemented search options available in custom-upgrade of web interface. Custom-upgraded web in- terface of OCWB and ...
    ... Springer, 13–25. Miloš V. Utvić, Ranka M. Stanković, Aleksandra Đ. Tomašević, Mihailo Đ. Škorić, Biljana Đ. Lazić THE CORPUS SEARCH BASED ON USAGE OF EXTERNAL LEXICAL RESOURCES THROUGH WEB SERVICES Summary Тhis paper explores a hybrid approach to corpus search illustrated by application of corpus tools ...
    ... Serbian Wordnet) through RESTful web services. Conse- quently, if necessary, user query containing lemma X can be expanded with lemmas such that specified semantic relation (synonymy, antonymy, hypernymy/ hyponymy) holds between each lemma that has been added and the lemma X. ...

  • Terminology Acquisition and Description Using Lexical Resources and Local Grammars

    Cvetana Krstev, Ranka Stanković, Ivan Obradović, Biljana Lazić (2015)
    Acquisition of new terminology from specific domains and its adequate description within terminological dictionaries is a complex task, especially for languages that are morphologically complex such as Serbian. In this paper we present an approach to solving this task semi-automatically on basis of lexical resources and local grammars developed for Serbian. Special attention is given to automatic inflectional class prediction for simple adjectives and nouns and the use of syntactic graphs for extraction of Multi-Word Unit (MWU) candidates for ...
    ... g device measured from the vertical excavator rotation axis to the front edge of the caterpillar”. 4.2 Extraction of MWUs from domain texts The extraction of MWUs from a text is preceded by the retrieval of new simple word terms from it and their incorporation in the existing system of morphological ...
    ... reason, in the case of ambiguous recognition we always give precedence to the more probable case. For instance, for 2-component MWUs the precedence is: AXN, 2XN, N2X, NXN. As a rule, we are looking for the longest match for a MWU, that is, if a text matches an Proceedings of the conference ...
    ... X., Sasaki, Y., Tonoike, M., Sato, S., & Utsuro, T. (2006). Compiling French-Japanese Terminologies from the Web. Paper presented at the 11 th Conference of the European Chapter of the Association for Computational Linguistics - EACL. Rodrıguez, F. M. B., Noya, E. D., Otero, P. G., Martınez ...

  • From post-disaster landslides inventory to open landslides data

    Biljana Abolmasov, Miloš Marjanović, Uroš Đurić, Jelka Krušić (2021)

  • Rule-based Automatic Multi-word Term Extraction and Lemmatization

    Ranka Stanković, Cvetana Krstev, Ivan Obradović, Biljana Lazić, Aleksandra Trtovac (2016)
    In this paper we present a rule-based method for multi-word term extraction that relies on extensive lexical resources in the form of electronic dictionaries and finite-state transducers for modelling various syntactic structures of multi-word terms. The same technology is used for lemmatization of extracted multi-word terms, which is unavoidable for highly inflected languages in order to pass extracted data to evaluators and subsequently to terminological e-dictionaries and databases. The approach is illustrated on a corpus of Serbian texts from ...
    term extraction, terminology, multi-word units, lemmatization, finite-state transducers
    ... stored in a SQL Server database. The architecture of the software solution depicted in Figure 2 is based on web services, thus enabling other applications to use some of them, such as indexing or document information retrieval, for term extraction. The current application is developed and ...
    ... our future work we will concentrate on:  Finalization of the web application;  Improvement of the precision of correct lemma production (development of additional strategies to avoid offering of incorrect lemmas). For instance, our results showed that at the end we obtained just a few (11) lemmas ...
    ... oblogom trake are extracted from a text, then we know that the MWT has singular forms (due to the second MWT) and the lemma has to be in the singular. But, if only the form oblogama trake is extracted we know that the MWT has plural forms and we presume that the lemma is also in plural; however ...

  • Advantages and challenges in presenting mathematical content using EDX platform

    Marija Radojičić, Ivan Obradović, Ranka Stanković, Olivera Kitanović, Roberto Linzalone (2016)
    ... and setting up indentations. Besides the basic editor, the creator of materials can use html view of text. In that case the creator has more opportunities in editing text but it demands creator’s basic knowledge of html. Task component offers a few on board frameworks for different types ...
    ... CONTENT USING EDX-BAEKTEL PLATFORM Over the last few years, mathematical content on the web is increasing, which means that production and exploitation of mathematical content using information technology (IT) is in progress [6]. Experts stress the importance of using TPACK framework (Image ...
    ... such as text, video, task or discussion. In the course “Preparation for entry exam” we mostly used a combination of text component and task component. The text component contains an editor for writing plain text, with basic editing functions, such as choosing fonts and size of text, adding ...