Претрага
175 items
-
A Data Driven Approach for Raw Material Terminology
Olivera Kitanović, Ranka Stanković, Aleksandra Tomašević, Mihailo Škorić, Ivan Babić, Ljiljana Kolonja (2021)The research presented in this paper aims at creating a bilingual (sr-en), easily searchable, hypertext, born-digital, corpus-based terminological database of raw material terminology for dictionary production. The approach is based on linking dictionaries related to the raw material domain, both digitally born and printed, into a lexicon structure, aligning terminology from different dictionaries as much as possible. This paper presents the main features of this approach, data used for compilation of the terminological database, the procedure by which it has ...sirovine, rudarstvo, terminologija, rečnik, terminološka aplikacija, mobilna aplikacija, digitizacija, leksički podaci, korpusi, otvoreni povezani podaci... few such dictionaries in the Serbian language, as most of the published Serbian terminological dictionaries are only translational (bilingual or multilingual). An ongoing activity is the adaptation of English definitions, which are the most comprehensive in DMMRT, to Serbian, in the post-editing phase ...
... Natural Language Processing (NLP), to develop a semi-automatic pipeline for dictionary production. The approach is focused on raw material terminology, with an emphasis on terminology related to the mining industry, as a case study, the main goal being to cover Serbian and bilingual English-Serbian terminology ...
... Sketch-engine [9] for several languages, but has not yet been used for Serbian. A similar approach to the one outlined in this paper was applied in development of the Sõnaveeb language portal of the Institute of the Estonian Language, which contains data from a number of dictionaries and termbases, with ...Olivera Kitanović, Ranka Stanković, Aleksandra Tomašević, Mihailo Škorić, Ivan Babić, Ljiljana Kolonja. "A Data Driven Approach for Raw Material Terminology" in Applied Sciences, MDPI AG (2021). https://doi.org/10.3390/app11072892
-
Combining Heterogeneous Lexical Resources
... tasks of the Natural Language Processing Group at the Faculty of Mathematics, University of Belgrade is the development of various lexical resources. Among them the two most important ones are: the system of morphological dictionaries of Serbian (SMD) in Intex format and the Serbian wordnet (SWN) developed ...
... 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. XPath treats an XML document as a tree of interrelated branches and nodes. A node in a XML document can be an element ...
... started good many years before WN, so it more thoroughly covers the language. As a consequence, the Serbian MD can benefit less form the WN then vice versa. For that reason, the production of the fully semantically marked Serbian DELAS has been postponed until the two resources will become comparable ...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)
-
Softverski alati za korišćenje resursa za srpski jezik
Ivan Obradović, Ranka Stanković (2008)... the most important lexical re- sources for Serbian developed within the Human Language Technology Group. More precisely, about the three basic resources encompassed by WS4LR and WS4QE, namely the system of mor- phological dictionaries of Serbian, the Serbian wordnet and aligned texts. 2.1 Morphological ...
... in one language (for example Serbian) may be created on basis of an existing synset in another language (for example English). In order to support this feature, the module en- ables the usage of bilingual, parallel word lists which can help in translation of synset literals in one language synset ...
... BalkaNet languages are spoken, but also from France and Netherlands. A national development team was formed for each language, and in the case of Serbian this team was the Human Language Technology Group at the University of Belgrade. Upon the termination of this project, the development of SWN contin- ...Ivan Obradović, Ranka Stanković. "Softverski alati za korišćenje resursa za srpski jezik" in INFOteka: časopis za informatiku i bibliotekarstvo, Belgrade, Serbia : Zajednica biblioteka univerziteta u Srbiji (2008)
-
A Description of Morphological Features of Serbian: a Revision using Feature System Declaration
In this paper we discuss some well-known morphological descriptions used in various projects and applications (most notably MULTEXT-East and Unitex) and illustrate the encountered problems on Serbian. We have spotted four groups of problems: the lack of a value for an existing category, the lack of a category, the interdependence of values and categories lacking some description, and the lack of a support for some types of categories. At the same time, various descriptions often describe exactly the same ...... (2008). Unitex 2.1 User Manual, http://www-igm.univ-mlv.fr/~unitex/UnitexManual2.1 .pdf. Popović, Z. (2009) Taggers Applied On Texts On Serbian Language, Language Tools And Machine Learning. In Infotheca, Vol. X, No. 2, (to appear). Przepiórkowski, A. and Woliński, M. (2003) A Flexemic Tagset For ...
... 07 Language resource management - Feature Structures – Part 2: Feature System Declaration, ISO/TC 37/SC 4. ISO. (2009) ISO 12620 Terminology and other language and content resources – Data Categories – Specification of data categories and management of a data category registry for language resources ...
... the satisfactory solution. 1. Motivation Description of morphological features of a language is a prerequisite for many NLP applications. This description can be simple or complex depending both on a language and application in question. Considerable efforts in standardizing such a description ...Cvetana Krstev, Ranka Stanković, Vitas Duško. "A Description of Morphological Features of Serbian: a Revision using Feature System Declaration" in Proceedings of the 5th International Conference on Language Resources and Evaluation, LREC 2010, Valetta, Malta : European Language Resources Association (2010)
-
A Tool for Enhanced Search of Multilingual Digital Libraries of E-journals
This paper outlines the main features of Bibliša, a tool that offers various possibilities of enhancing queries submitted to large collections of TMX documents generated from aligned parallel articles residing in multilingual digital libraries of e-journals. The queries initiated by a simple or multiword keyword, in Serbian or English, can be expanded by Bibliša, both semantically and morphologically, using different supporting monolingual and multilingual resources, such as wordnets and electronic dictionaries. The tool operates within a complex system composed ...... can be either Serbian or English, thus they switch places as the source and target language. The example in Figure 1 shows a TU from an INFOtheca journal article in English translated into Serbian: Figure 1. A translation unit (TU) from text in English translated into Serbian Besides TMX ...
... simple and multiword keywords in more than one language. In addition to that, user queries can be expanded, both semantically and morphologically, the latter being very important in highly inflective languages, such as Serbian. Open access Serbian scientific journals are increasingly present ...
... metadata All metadata, except language independent data, such as the numeration metadata (, , , , ), the and , are entered in both languages (Serbian and English), using the attribute xml:lang to denote the language of the content (see Figure 2) ... Ranka Stanković, Cvetana Krstev, Ivan Obradović, Aleksandra Trtovac, Miloš Utvić. "A Tool for Enhanced Search of Multilingual Digital Libraries of E-journals" in Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012, May 2012, Istanbul, Turkey, Istanbul, Turkey : European Language Resources Association (2012)
-
OntoLex Publication Made Easy: A Dataset of Verbal Aspectual Pairs for Bosnian, Croatian and Serbian
Ovaj rad predstavlja novi jezički resurs za pretraživanje i istraživanje verbalnih aspektnih parova u BCS (bosanskom, hrvatskom i srpskom), kreiran korišćenjem principa Lingvističkih Povezanih Otvorenih Podataka (LLOD). Pošto ne postoji resurs koji bi pomogao učenicima bosanskog, hrvatskog i srpskog kao stranih jezika da prepoznaju aspekt glagola ili njegove parove, kreirali smo novi resurs koji će korisnicima pružiti informacije o aspektu, kao i link ka aspektnim parovima glagola. Ovaj resurs takođe sadrži spoljne linkove ka monolingvalnim rečnicima, Wordnetu i BabelNetu. ...Ranka Stanković, Maxim Ionov, Medina Bajtarević, Lorena Ninčević. "OntoLex Publication Made Easy: A Dataset of Verbal Aspectual Pairs for Bosnian, Croatian and Serbian" in Proceedings of the 9th Workshop on Linked Data in Linguistics @ LREC-COLING 2024, Turin, 20-25 May 2024, ELRA and ICCL (2024)
-
Quantitative analysis of syllable properties in Croatian, Serbian, Russian, and Ukrainian
Biljana Rujević, Marija Kaplar, Sebastijan Kaplar, Ranka Stanković, Ivan Obradović, Jan Mačutek (2021)Biljana Rujević, Marija Kaplar, Sebastijan Kaplar, Ranka Stanković, Ivan Obradović, Jan Mačutek. "Quantitative analysis of syllable properties in Croatian, Serbian, Russian, and Ukrainian" in Language and Text: Data, models, information and applications, John Benjamins Publishing Company (2021). https://doi.org/10.1075/cilt.356.04ruj
-
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 ...Ranka Stanković, Cvetana Krstev, Branislava Šandrih Todorović, Duško Vitas, Mihailo Škorić, Milica Ikonić Nešić. "Distant Reading in Digital Humanities: Case Study on the Serbian Part of the ELTeC Collection" in Proceedings of the Language Resources and Evaluation Conference, June 2022, Marseille, France, European Language Resources Association (2022)
-
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)
-
From ELTeC Text Collection Metadata and Named Entities to Linked-data (and Back)
In this paper we present the wikification of the ELTeC (European Literary Text Collection), developed within the COST Action ``Distant Reading for European Literary History'' (CA16204). ELTeC is a multilingual corpus of novels written in the time period 1840—1920, built to apply distant reading methods and tools to explore the European literary history. We present the pipeline that led to the production of the linked dataset, the novels’ metadata retrieval and named entity recognition, transformation, mapping and Wikidata population, ...Milica Ikonić Nešić, Ranka Stanković, Christof Schöch and Mihailo Škorić. "From ELTeC Text Collection Metadata and Named Entities to Linked-data (and Back)" in Proceedings of The 8th Workshop on Linked Data in Linguistics within the 13th Language Resources and Evaluation Conference, June 2022, Marseille, France, European Language Resources Association (2022)
-
Improvement of geodatabase queries within GeolISS
Ranka Stanković (2008)... expansion of the query, very important in highly inflective languages, such as Serbian. The geological dictionary, developed within GeolISS, supports semantic and multilingual expansions of the query. The Human Language Technology group at the University of Belgrade (HLT) has been developing various ...
... Vitas D., G. Pavlović-Lažetić, C. Krstev, Lj. Popović, I. Obradović (2003): „Processing Serbian Written Texts: An Overview of Resources and Basic Tools“, Proceedings of the International Workshop on Balkan Language Resources and Tools, Thessaloniki, Greece, November 2003, S. Piperidis, V. Karakaletsis ...
... Resources in Developing Serbian Wordnet”, Romanian J. Information Science and Technology, Romanian Academy, vol. 7, No. 1–2, pp. 147–161, (2004) [12] Krstev, C., Vitas, D., Maurel, D., Tran, M. (2005). “Multilingual Ontology of Proper Names”. In Proc. of Second Language & Technology Conference ...Ranka Stanković. "Improvement of geodatabase queries within GeolISS" in Review of the National Center for Digitization, Beograd : Faculty of Mathematics, Belgrade (2008)
-
A Mathematical Learning Environment Based on Serbian Language Resources
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 ...... Environment Based on Serbian Language Resources Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] A Mathematical Learning Environment Based on Serbian Language Resources | Radojičić ...
... Sciences, Čačak, Serbia, 25-27th May 2018 Session 2: IT Education and Practice UDC: 51-7 248 A Mathematical Learning Environment Based on Serbian Language Resources Marija Radojičić1*, Ivan Obradović2, Ranka Stanković2, Miloš Utvić3, Sebastijan Kaplar1 1 University of Novi Sad/Faculty of Technical ...
... of this content. It relies on existing lexical resources, morphological e-dictionaries and WordNet of Serbian, which have been developed within the University of Belgrade Human Language Technology group for several decades [1], as well as a newly developed glossary, Termi. The system is ...Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan. "A Mathematical Learning Environment Based on Serbian Language Resources" in Proceedings of the 7th International Scientific Conference Technics and Informatics in Education, Faculty of Technical Sciences, Čačak (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 Retrieval... semantic and morphological expansion of the query, the latter being very important in highly inflective languages, such as Serbian. Wordnets can also be used for adding another language to a query, if appropriate, thus making the query bilingual. Problems encountered in retrieving documents of interest ...
... precision in retrieving documents from the web we have developed WS4QE (Work Station for Query Expansion) which uses various language resources we have developed for Serbian (Krstev et al., 2008). These resources include morphological e-dictionaries and finite state transducers, which offer the ...
... in Cyrillic (Figure 3). 2 For reasons of flexibility letters specific for the Serbian language ć, č, š ,ž ,đ, dž, lj and nj, are internally coded as cx, cy, sx, zx, dx, dy, lx and nx, respectively) 222 Figure 2. Semantic expansion ...Krstev 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)
-
Infotheca (Q25460443) in Wikidata
Ranka Stanković, Lazar Davidović (2021)Vikipodaci su baza znanja Zadužbine Vikimedija koja predstavlja zajednički izvor različitih vrsta podataka koje koriste ne samo drugi Vikipedijini projekti, već sve više i brojne aplikacije semantičkog veba. U ovom radu ćemo prezentovati primer integracije Vikipodataka sa digitalnim bibliotekama i eksternim sistemima, kao i mogućnost ubrzanja pripreme i unosa podataka na primeru radova iz časopisa za digitalnu humanistiku Infoteka.... entry of data about the results of the research in the domain of digital humanities in Serbia, as well as about old Serbian novels, so as to increase the visibility of both the Serbian language, our cultural heritage and the results of the research in Serbia and certainly pave the way for many other data ...
... (P1476), in English and Serbian (both scripts, Cyrillic and Latin, for the sake of search); – Main subject of the creative work (P921), key words, where the existing ones are linked and new ones are added as instances with labels in Serbian and English; – Publisher (P123); – Language of the work or name ...
... COST Action CA16204 (2017-2021) metadata about Serbian novels included in the srpELTEC corpus is being entered into the knowledge base (Krstev et al. 2019) and Wikidata linked to various applications, one of which is Au- rora.14 Members of JeRTeh Language Resources and Technologies Society15 too contributed ...Ranka Stanković, Lazar Davidović. "Infotheca (Q25460443) in Wikidata" in Infotheca, Faculty of Philology, University of Belgrade (2021). https://doi.org/10.18485/infotheca.2021.21.1.5
-
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 ...... was written in C# programming language and it can be ran on Windows platform, using any version of the operating system that runs to 64 bit. The interface is user-friendly and entirely in Serbian. The goal in designing this software was that any researcher who speaks Serbian can use it independently, create ...
... use in their messages (in the form of emoti- cons or language-universal phrases) and assigning values of sentiment polar- ity to terms in which those determiners are located. As the determiners are language-independent, the system would be language-independent as well. If it turns out to be valid, this ...
... of Belgrade 1 Introduction When creating natural language understanding software, there are two widely accepted approaches: – Software that does not have a deep understanding of the meaning of written text, but only the grammar of the language that text is written on, which enables wider application ...Mihailo Škorić. "Classification of Terms on a Positive-Negative Feelings Polarity Scale Based on Emoticons" in Infotheca, Faculty of Philology, University of Belgrade (2017). https://doi.org/10.18485/infotheca.2017.17.1.4
-
Knowledge and Rule-Based Diacritic Restoration in Serbian
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%).... Knowledge and Rule-Based Diacritic Restoration in Serbian Cvetana Krstev, Ranka Stanković, Duško Vitas Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] Knowledge and Rule-Based Diacritic Restoration in Serbian | Cvetana Krstev, Ranka Stanković, Duško Vitas | ...
... RuThes thesaurus (Loukachevitch and Dobrov, 2014) and created for automatic processing of documents in information- analytical systems and natural language processing. These resources are linguistic ontologies uniting some principles of their organization from WordNet, information-retrieval thesauri ...
... generation allows better understanding of the differences between representation models of the thesauri. 2. Existing Russian Thesauri For the Russian language, there were at least four known projects for creating a wordnet. In the Russ- Net project (Azarowa, 2008), the authors planned to create a Russian ...Cvetana Krstev, Ranka Stanković, Duško Vitas. "Knowledge and Rule-Based Diacritic Restoration in Serbian" 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): 41-51
-
Serbian NER&Beyond: The Archaic and the Modern Intertwinned
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 ...... Repository is available at: www.dr.rgf.bg.ac.rs Proceedings of Recent Advances in Natural Language Processing, pages 1252–1260 Sep 1–3, 2021. https://doi.org/10.26615/978-954-452-072-4_141 1252 Serbian NER&Beyond: The Archaic and the Modern Intertwinned Branislava Šandrih Todorović University ...
... guration. In our case, the model’s language was 12Translates as: In the meantime, Haji-Đera entered the room to wish agas good morning, when the monastery servant started offering coffee and brandy. 13Quick-start spaCy3 widget, https://spacy.io/usage/training#quickstart Serbian, containing the ner component ...
... Todorović, Cvetana Krstev, Ranka Stanković, Milica Ikonić Nešić | Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Methods and Applications | 2021 | | 10.26615/978-954-452-072-4_141 http://dr.rgf.bg.ac.rs/s/repo/item/0005139 ...Branislava Šandrih Todorović, Cvetana Krstev, Ranka Stanković, Milica Ikonić Nešić. "Serbian NER&Beyond: The Archaic and the Modern Intertwinned" in Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Methods and Applications, INCOMA Ltd. Shoumen, BULGARIA (2021). https://doi.org/10.26615/978-954-452-072-4_141
-
Fourth Summer Datathon on Linguistic Linked Open Data
Tijana Radović, Ranka Stanković (2023)The 4th Summer Datathon on Linguistic Linked Open Data (SD-LLOD-22) was held in Spain, in Cersedilla near Madrid, in May 2022, and organized by the COST Action NexusLinguarum. The school gathered interested researchers, academics, students who wanted to acquire and/or expand their knowledge in the field of linguistic linked data science. During the school, a spectrum of topics from the field of linked data was presented, from various ontologies, through document integration, annotation and natural language text processing tools ...Tijana Radović, Ranka Stanković. "Fourth Summer Datathon on Linguistic Linked Open Data" in Infotheca, Faculty of Philology, University of Belgrade (2023). https://doi.org/10.18485/infotheca.2023.23.1.6
-
Development Of The Serbian Geological Resources Portal
... and GIS tech- nologies. The largest part was realized with the use of the PHP (Hypertext Preprocessor) script language on server side and the XHTML (eXtensible HyperText Markup Language) language on the client side. In addition to this, the part of the web portal pertaining to geological terminology and ...
... JavaScript functions, while the search engine was developed with the use of PHP script language and AJAX. By using HTML and CSS for markup, JavaScript for the access to DOM elements, XML (Extensible Markup Language) or JSON (JavaScript Object Notation), data is downloaded from the server and the final ...
... 2023-10-14 03:28:12 Development Of The Serbian Geological Resources Portal Ranka Stanković, Jelena Prodanović, Olivera Kitanović, Velizar Nikolić Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] Development Of The Serbian Geological Resources Portal | Ranka Stanković ...Ranka Stanković, Jelena Prodanović, Olivera Kitanović, Velizar Nikolić. "Development Of The Serbian Geological Resources Portal" in Proceedings of the 17th Meeting of the Association of European Geological Societies, Belgrade, Serbia : The Serbian Geological Society (2011)
-
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