Претрага
319 items
-
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 ...... finite state transducers, can also be used to aid the user in developing and refining the wordnet. Keywords Wordnet development, language resource integration, HLT tools 1. Introduction The first wordnet, namely the Princeton WordNet (PWN), or simply WordNet, was conceived in 1985 by George ...
... 3 http://www.illc.uva.nl/EuroWordNet/sample.html 4 http://nlp.fi.muni.cz/projekty/visdic/ 3. A Multifunctional Language Resource Tool 3.1 Motivation The Human Language Technology group at the University of Belgrade has been developing various lexical resources over quite a long period ...
... would facilitate the maintenance, exploitation and integration of available resources as well as their further development. Embarking on this task, the HLT group produced an integrated and easily adjustable tool, the workstation for language resources, labeled WS4LR, which greatly enhances the ...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)
-
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
-
A bilingual digital library for academic and entrepreneurial knowledge management
A generic knowledge management process of organization, storage and retrieval of knowledge can suitably be fitted in a digital library. In the digital and knowledge age digital libraries can be used in knowledge management to handle intellectual assets and support knowledge creation. A multilingual digital library either stores content in more than one language or provides multilingual query access to monolingual content. In Serbia 18 of 308 scientific journals regularly published are bi-lingual, with papers simultaneously being in English ...... of Philology, Her scientific field is Human Language Technologies (HLT) and technology enhanced learning (TEL). She published one book and more than 100 scientific papers, most of them related to natural language processing, more specifically to language resources development and their application ...
... components In designing Bibliša special attention is given to its language support component. It supports various aspects of multilingual libraries: its content is not only multilingual, but also aligned and it can be searched in any language. The proposed tool basically consists of the following components: ...
... The System retrieves terms that match the given keywords from the lexical resources of a query language and then finds their equivalents in another language based on inter- lingual relations established in the lexical resources. After refinement of a query (e.g. deleting or ...Ranka Stanković, Cvetana Krstev, Biljana Lazić, Dalibor Vorkapić. "A bilingual digital library for academic and entrepreneurial knowledge management" in Proceeding of 10th International Forum on Knowledge Asset Dynamics — IFKAD 2015: Culture, Innovation and Entrepreneurship: connecting the knowledge dots, Bari, Italy, 10-12 June 2015, Bari : IFKAD (2015)
-
Vulnerability methods in hard rock formation as a basis for groundwater risk assessment – from resource to source
Groundwater in a hard rock formation is most endangered at places where a potential source can discharge contaminants that can reach the saturated zone of an aquifer. In these circumstances, an essential tool for groundwater protection is the contamination risk map. This map is based on the integration of two maps: a hazards map, i.e., map of potential sources of contamination and a vulnerability map. The selection of a proper vulnerability method is an important task since the resulting ...karta rizika od kontaminacije, ranjivosti podzemnih voda, DRASTIC, EPIK, PI, COP, Nacionalni park TaraVladimir Živanović, Igor Jemcov, Veselin Dragišić. "Vulnerability methods in hard rock formation as a basis for groundwater risk assessment – from resource to source" in Geologia Croatica, Croatian Geological Survey (2022). https://doi.org/10.4154/gc.2022.23
-
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 ...... eu/MWSA. Keywords: lexical semantic resources, sense alignment, lexicography, language resource 1. Introduction Lexical semantic resources (LSRs) are knowledge reposi- tories that provide the vocabulary of a language in a de- scriptive and structured way. One of the famous examples of LSRs are ...
... et al., 2012) and with the Digital Dictionary of the German Language (Digitales Wörterbuch der Deutschen Sprache (Klein and Geyken, 2010)) (Henrich et al., 2014). Gurevych et al. (2012) present UKB–a large-scale lexical-semantic resource con- taining pairwise sense alignments between a subset of ...
... meaning. The annotator found the most challenging aspect of the task to lie in the necessity of having to choose the type of match- 3237 Language Resource Nouns Verbs Adjectives Adverbs Other All Basque Wordnet 929 (6836) 0 (0) 0 (0) 0 (0) 0 (0) 929 (6836) Basque Euskal Hiztegia 971 (7754) 0 (0) ...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)
-
The Nooj System as Module within an Integrated Language Processing Environment
... transducers as the morphological resource and Serbian wordnet as the resource for semantic expansion. The user can also use the translation equivalence option which is aimed at locating equivalences in target language for occurrences found in the source language. This is done on the basis of data ...
... has so far been used mainly for Serbian, WS4LR is not language dependent and can be successfully used for resources in other languages provided that they follow the described formats and methodologies. The integration of NooJ with other language resources was aimed in the first place at integrating ...
... would facilitate the maintenance, exploitation and integration of available resources as well as their further development. Embarking on this task, the HLT group produced an integrated and easily adjustable tool, the workstation for language resources, labeled WS4LR, which greatly enhances the ...Ranka Stanković, Duško Vitas, Cvetana Krstev. "The Nooj System as Module within an Integrated Language Processing Environment" in Proceedings of the 2007 International Nooj Conference, Cambridge Scholars Publishing (2008)
-
GIS Application Improvement with Multilingual Lexical and Terminological Resources
... tool, a workstation for language resources, named WS4LR, which greatly enhances the potential of manipulating each particular resource as well as several resources simultaneously (Krstev et al., 2008). This tool has already been successfully used for various language processing related tasks ...
... Geology E-mail: {ranka, ivano, olja}@rgf.bg.ac.rs Abstract This paper introduces the results of integration of lexical and terminological resources, most of them developed within the Human Language Technology (HLT) Group at the University of Belgrade, with the Geological information system of Serbia ...
... been tested with Serbian, which describes regional information in the local language, and English, used for sharing geographic information with the world, although the geological vocabulary offers the possibility for integration of other languages as well. The resources also enable semantic and morphological ...Ranka Stanković, Ivan Obradović, Olivera Kitanović. "GIS Application Improvement with Multilingual Lexical and Terminological Resources" in Proceedings of the 5th International Conference on Language Resources and Evaluation, LREC 2010, Valetta, Malta, May 2010, Valetta, Malta : European Language Resources Association (2010)
-
LRMI markup of OER content within the BAEKTEL project
... Data”, which connects “things” rather than documents. The machine-readable datasets of the Semantic Web are used in: search engines, data integration, resource discovery and classification, cataloging, intelligent software agents, content rating, Big Data processing, etc. [9] The union of ...
... purpose of the resource, for example ‘assignment’ or ‘group work’. The interactivity type describes the predominant mode of learning, like ‘active’, ‘expositive’ or ‘mixed’. If a learning resource is derived from another resource, property based on url is used. The learning resource type describes ...
... Learning Resource Metadata Initiative (LRMI) [5]. The focus of this paper is on LRMI metadata and their management in the context of BAEKTEL OER framework, which is described in more detail in section 2. In section 3 a review of semantic annotation implementation with examples of resource tagging ...Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić. "LRMI markup of OER content within the BAEKTEL project" in The Sixth International Conference on e-Learning (eLearning-2015), September 2015, Belgrade, Serbia, Belgrade : Belgrade Metropolitan Univesity (2015)
-
Building learning capacity by blending different sources of knowledge
... n, language of the resource content, date when the resource was made available to the public, contributor and type of resource are general data, originating from the DC standard. Within general data, a unique code is defined to provide unambiguous identification and access to the resource. ...
... represents a textual resource that BMP language support system makes use of. The language support system handles various types of requests issued by users, usually in the form of a query. The requests are handled by WSDL (Web Services Description Language) described Language Web Service, basically ...
... globalization and European integration, and represents a holistic approach that takes into account all the languages a learner may use, as opposed to the more traditional approach looking at one language at a time (Cenoz & Gorter, 2011). Specifically, providing language resources in WB languages ...Ivan Obradović, Ranka Stanković, Olivera Kitanović, Dalibor Vorkapić. "Building learning capacity by blending different sources of knowledge" in International Journal of Learning and Intellectual Capital (2016). https://doi.org/10.1504/IJLIC.2016.075698
-
Two approaches to compilation of bilingual multi-word terminology lists from lexical resources
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 ...Branislava Šandrih, Cvetana Krstev, Ranka Stanković. "Two approaches to compilation of bilingual multi-word terminology lists from lexical resources" in Natural Language Engineering, Cambridge University Press (CUP) (2020). https://doi.org/10.1017/S1351324919000615
-
A Tel Platform Blending Academic And Entrepreneurial Knowledge
... cognitive student and teacher workload in TEL. Providing means for easy integration of learning content from different sources was also necessary. 4. THE LANGUAGE SUPPORT SYSTEM In BAEKTEL, special attention is given to its language support system. This is primarily a consequence of the need to ...
... Namely, due to the combined effect of globalization and European integration the need for enhancing multilingual business and academic communication is growing. In contrast to more traditional approaches that look at one language at a time, a holistic approach is now being proposed that takes ...
... mentioned that due to the complex Serbian grammar the language support system also features grammars implemented through finite state automata, finite state transducers and compound inflection rules. The language resources in the BAEKTEL language support system are managed by a web application ...Ivan Obradović, Ranka Stanković, Jelena Prodanović, Olivera Kitanović. "A Tel Platform Blending Academic And Entrepreneurial Knowledge" in Proceedings of the The Fourth International Conference on e-Learning (eLearning-2013), September 2013, Belgrade, Serbia, Belgrade, Serbia : Belgrade Metropolitan University (2013)
-
Combining Heterogeneous Lexical Resources
... i.e. first in a hierarchy. In this environment an Integrated Language Resource Management Tool (ILReMaT) has been developed. This tool supports the development of a wordnet in accordance with the EWN, and enables its integration with other lexical resources. This tool has been designed as a ...
... instance, glosses) etc. Besides that, this tool enables the integration of a with bilingual word list in the development process, which can help in the translation of literal strings and in the checking of the existing cross- language relations. Various editing tasks can be performed on a synset ...
... the other hand, the XML Schema definition language (XSD) enables the definition of the structure and data types of XML documents. Figure 1 shows the graphical representation of XSD schema of Serbian WN. The XML Path Language (XPath) provides a language for addressing parts of an XML document ...Cvetana Krstev, Duško Vitas, Ranka Stanković, Ivan Obradović, Gordana Pavlović-Lažetić. "Combining Heterogeneous Lexical Resources" in Proceedings of the Fourth Interantional Conference on Language Resources and Evaluation, Lisabon, Portugal , May 2004, vol. 4, ELRA - European Language Resources Association (2004)
-
A Twitter Corpus and Lexicon for Abusive Speech Detection in Serbian
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 ...... activities or as a derogatory word to insult someone. Information integration beyond the level of dictionaries and across the language resource community has become an important concern. The most promising technology for information integration is the Linked (Open) Data (LOD) paradigm that is used for publishing ...
... and low-resource languages such as Serbian. The main contribution of this work is the creation of the AbCoSER, the first abusive speech corpus in Serbian, that will, together with abusive speech lexicon, enable the development of automatic abusive speech detection systems for the Serbian language. In the ...
... a general data set convenient for the detection of a broad range of abusive topics. We already used this resource for the detection of abusive triggers and the augmentation of the abusive language lexicon. D. Jokić, R. Stanković, C. Krstev, and B. Šandrih 13:3 1.2 Related work In the past two decades ...Danka Jokić, Ranka Stanković, Cvetana Krstev, Branislava Šandrih. "A Twitter Corpus and Lexicon for Abusive Speech Detection in Serbian" in 3rd Conference on Language, Data and Knowledge (LDK 2021), MDPI AG (2021). https://doi.org/10.4230/OASIcs.LDK.2021.13
-
Utilizing sewage wastewater heat in district heating systems in Serbia: effects on sustainability
Marija Živković, Dejan Ivezić (2021)Transformation of the heating sector is recognized as being essential for ensuring reliable and afordable energy services provided with reduced consumption of energy sources and diminished impact on the environment and less import dependency. The possibility of utilizing energy sources that otherwise would be wasted needs to be considered and treated as a big advantage of district heating systems. Despite many advantages, sewage wastewater heat is still a mostly unused resource at the global level and a totally unused ...рекуперација топлоте из отпадних вода, систем даљинског грејања, топлотне пумпе, енергетске уштеде, емисија угљендиоксида, енергетска безбедност, Србија... unused resource at the global level (Intelligent energy Europe 2017). More intensive utilization of sewage wastewater heat could be achieved by the integration of heat pumps in district heating (DH) systems (Averfalk et al. 2017). Sayegh et al.’s (2018) four scenarios of possible integration of heat ...
... optimization, focusing on performance of the system and environmental analysis. Koll- mann et al. (2017) proposed a novel method to assess the integration of wastewater treatment plants (WWTPs) into local energy supply concepts. The method addresses spatial, economic and environmental perspectives ...
... n phase and WWTP loca- tion selection. In this paper, the proposed methodology was applied for Serbia as a case study, assuming a scenario of integration of heat pumps in the existing district heating systems with- out major changes. Currently in Serbia, sewage waste heat is not utilized at all. ...Marija Živković, Dejan Ivezić. "Utilizing sewage wastewater heat in district heating systems in Serbia: effects on sustainability" in Clean Technologies and Environmental Policy, Springer Science and Business Media LLC (2021). https://doi.org/10.1007/s10098-021-02063-6
-
Resource-based WordNet Augmentation and Enrichment
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 ...... comprehensiveness of the resource used in the alignment process (Hristea, 2007). Different methods and resources can be used for alignment. One of the common approaches is to take PWN as the source for alignment, and a bilingual dictionary of English and the target language. There are, however, several ...
... n API based on Google Language Translation API, into: ENG30-08331011-n | sud koji je nadležan za pravičnost | kancelarija ; sudski ured If a Serbian translational equivalent for a PWN literal obtained by Google Translation is not of- fered by any other bilingual resource, it is taken into account ...
... Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In Chair), N. C. C., Choukri, K., Maegaard, B., Mariani, J., Odijk, J., Piperidis, S., Rosner, M., and Tapias, D., Eds., Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10) ...Ranka Stanković, Miljana Mladenović, Ivan Obradović, Marko Vitas, Cvetana Krstev. "Resource-based WordNet Augmentation and Enrichment" in Proceedings of the Third International Conference Computational Linguistics in Bulgaria (CLIB 2018), May 27-29, 2018, Sofia, Bulgaria, Sofia : The Institute for Bulgarian Language Prof. Lyubomir Andreychin, Bulgarian Academy of Sciences (2018)
-
Development of terminological resources for expert knowledge: a case study in mining
Ljiljana Kolonja, Ranka Stanković, Ivan Obradović, Olivera Kitanović, Aleksandar Cvjetić. "Development of terminological resources for expert knowledge: a case study in mining" in Knowledge Management Research & Practice, Palgrave Macmillan (2015). https://doi.org/10.1057/kmrp.2015.10
-
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 ...... dictionaries meet, since both types should preferably use the same or compatible formal structure and markup language.2 This development led to further linking of lexical data and their integration with semantic resources, such as ontologies (McCrae et al., 2011). The DSA is rather special compared to ...
... database, language resources, dictionary, Serbian language 1 Introduction The first volume of the Dictionary of the Serbo-Croatian Standard and Vernacular Language (re- ferred to as the Dictionary of Serbian Academy or DSA), prepared and compiled by the Institute for the Serbian Language of the Serbian ...
... the Lexical Database Ranka Stanković1, Rada Stijović2, Duško Vitas1, Cvetana Krstev1, Olga Sabo2 1University of Belgrade, 2Institute for Serbian Language, Serbian Academy of Sciences and Arts E-mail: ranka.stankovic@rgf.bg.ac.rs, rada.stijovic@isj.sanu.ac.rs, vitas@matf.bg.ac.rs, cvetana@matf.bg ...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)
-
Improvement of geodatabase queries within GeolISS
Ranka Stanković (2008)... adjustable tool, a workstation for language resources, labeled WS4LR, which greatly enhances the potential of manipulating each particular resource as well as several resources simultaneously [9]. This tool has already been successfully used for various language processing related tasks including ...
... trends. First results of the integration of the WS4QE web service with GeolISS demonstrates that resources and tools developed within the HLT Group at the University of Belgrade can substantially improve query results for the GeolISS geodatabase. A further integration of developed lexical resources ...
... system of Serbia (GeolISS). The first section of this paper introduces the approach to GeolISS development, whose main goal is the integration of existing geologic archives, data from published maps on different scales, newly acquired field data, Intranet and Internet publishing of geologic information ...Ranka Stanković. "Improvement of geodatabase queries within GeolISS" in Review of the National Center for Digitization, Beograd : Faculty of Mathematics, Belgrade (2008)
-
Using technology for knowledge transfer between academia and enterprises
Ivan Obradović, Ranka Stanković (2014)... 4 The language support system The need for multilinguality of OER is a combined effect of globalization and European integration, favoring a holistic approach that takes into account all the languages a learner may use, as opposed to the more traditional approach looking at one language at a time ...
... multilingual, the latter often composed of aligned texts. Finally the web itself represents a textual resource that LSS makes use of. Specific features of Serbian grammar need corresponding language resources in the form of grammars. Grammars within LSS are implemented by the so called finite state ...
... inflection rules (Krstev, 2008). The language support system handles various types of requests issued by the tools from the learning management system, usually in the form of a query. The requests are handled by a WSDL (Web Services Description Language) described Language Web © Institute of Knowledge ...Ivan Obradović, Ranka Stanković. "Using technology for knowledge transfer between academia and enterprises" in Knowledge and Management Models for Sustainable Growth, Proc. of IFKAD 2014, 9th International Forum on Knowledge Asset Dynamics, 11-13 June 2013, Matera, Italy, Bari : IFKAD (2014)
-
An Integrated Environment for Management and Exploitation of Linguistic Resources
Ranka Stanković, Ivan Obradović (2009)... adjustment that WS4QE provides result from integration of several available re- sources. Both WS4QE and WS4LR, offer to the user the possibility to expand the query morphologically, semanti- cally, but also to another language (English). Besides, the user can further fine-tune ...
... tools. When the web is concerned, further development of WS4QE functions is underway, as well as the integration of developed functions and the corpus for Serbian language, which is also partly available on the web. Finally the devel- opment of a mobile application, for PDA devices ...
... of aligned texts, conversions from one coding scheme to another, and migration from one resource format to another. Although WS4LR has mainly been used for resources in Serbian, it is not a language dependent tool. All of its func- tions are usable for resources in other languages provided ...Ranka Stanković, Ivan Obradović. "An Integrated Environment for Management and Exploitation of Linguistic Resources" in Proceedings of the International Multiconference on Computer Science and Information Technology, Computational Linguistics – Applications Workshop (CLA09), Mrągowo, Poland, October 2009, Piscataway : IEEE (2009)