Претрага

Упит dcterms_subject_txt:text corpora

66 items

  • Terminological and lexical resources used to provide open multilingual educational resources

    Biljana Lazić, Danica Seničić, Aleksandra Tomašević, Bojan Zlatić (2016)
    Open educational resources (OER) within BAEKTEL (Blending Academic and Entrepreneurial Knowledge in Technology enhanced learning) network will be available in different languages, mostly in the languages of Western Balkans, Russian and English. University of Belgrade (UB) hosts a central repository based on: BAEKTEL Metadata Portal (BMP), 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 and OER repository on local edX ...
    otvoreni obrazovni resursi, leksički resursi, obrada prirodnih jezika, terminologija
    ... consists of morphological dictionaries, WordNet, domain specific terminological resources such as GeolISSterm, RudOnto, aligned texts in TMX format, corpora etc. Special attention will be given to Termi, newly developed application for terminology management. Keywords: Open Educational Resources, Lexical ...
    ... rely greatly on various NLP tools to help them cater to a large number of students from all over the world. These tools may include assessment of text and speech, writing assistants, automatic generation of exercises, wrap up questions and online instructional environments [3]. The main goal of ...
    ... transducers applied on domain corpus to extract terminology. Examples of patterns are presented in [15]. After applying these transducers on domain text extracted potential terms were evaluated. Results presented in previous paper were satisfying enough to speed up the development of a terminological ...

  • 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

  • Development of Open Educational Resources (OER) for Natural Language Processing

    Cvetana Krstev, Biljana Lazić, Ranka Stanković, Giovanni Schiuma, Miladin Kotorčević (2015)
    In this paper we present the development of an online course at the edX BAEKTEL platform named “Lexical Recognition in the Natural Language Processing (NLP)”. It is based on the course of the same name for PhD studies at the University of Belgrade, Faculty of Philology. There are not many courses in Computational Linguistics (CL) on OER platforms, and there is none in Serbian either for CL or NLP. We have developed this course in order to improve this ...
    E-Learning, Open Educational Resources, Computational Linguistics, Lexical Resources, edX
    ... but also in written form as parallel (multilingual) corpora of lessons and texts, supported by electronic terminological resources[10], services, and functionalities for searching and browsing of terminological resources and using them for text annotation. The project consortium 10 consists ...
    ... speech tagging and information extraction, question answering, text summarization, collocations and information retrieval, sentiment analysis and semantics, discourse, machine translation, regular expressions, language models, text classification, and name entity recognition. All of them combine ...
    ... them. Text analyses can be performed at the levels of strings, morphology, and syntax. Some of the functions are:  developing and applying electronic dictionaries of simple words and multi-word units;  pattern matching with queries in form of regular expressions and graphs;  text tra ...

  • Part of Speech Tagging for Serbian language using Natural Language Toolkit

    Ranka Stanković, Boro Milovanović (2020)
    Dok se razvijaju složeni algoritmi za NLP (obrada prirodnog jezika), osnovni zadaci kao što je označavanje ostaju veoma važni i još uvek izazovni. NLTK (Natural Language Toolkit) je moćna Python biblioteka za razvoj programa zasnovanih na NLP-u. Pokušavamo da iskoristimo ovu biblioteku za kreiranje PoS (vrsta reči) oznake za savremeni srpski jezik. Jedanaest različitih modela je kreirano korišćenjem NLTK API-ja za označavanje. Najbolji modeli se transformišu sa Brill tagerom da bi se poboljšala tačnost. Obučili smo modele na označenom ...
    obrada prirodnog jezika, mašinsko učenje, neuronske mreže
    ... each token in the text. The program that performs tagging is called tagger. The taggers can be created in multiple ways. In this paper, we will create a tagger for Serbian with a help of a Python library NLTK (Natural Language Toolkit). Besides just exposing more than 50 corpora and lexical resources ...
    ... of tagger models packaged in NLTK that can be trained. Every tagger has an evaluation procedure that strips down the tags from the given text, tags the text with the newly created tagger and reports the accuracy on all tokens. This measure will be used for comparing different taggers. The simplest ...
    ... 83 90.51 86.95 Training Time 1143s 1343s 3074s Useful tagger model is one which generalizes well to the text from the other domains. That’s why we tested our best taggers on the text that stayed out of the training and validation phases. Results can be seen in Figure 3. Fig. 3. Accuracy ...

  • An Integrated Environment for Management and Exploitation of Linguistic Resources

    Ranka Stanković, Ivan Obradović (2009)
    ... “highlighting”, namely by representing them in blue, in order to make them more easily recognizable in the text. The text in English is on the left hand side, and the corre- sponding text in Serbian on the right. Given the fact that the compound “poreska obaveza” was not in the dictionary of compounds ...
    ... all forms of literals of a chosen synset in a given text, with the possibility of adding hypernym literals. D. Aligned texts WS4LR contains a module for processing of parallel texts which have previously been aligned using the text align- ment tool XAlign. The module enables the tr ...
    ... house, nursery, glasshouse” from the corresponding synsets in English wordnet were included in query. B. Aligned text search When a bilingual query is applied to an aligned text, WS4QE generates a filtered aligned document in TMX for- mat. Namely, based on the expansion of the query, which ...

  • 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
    ... abusiveness are found in text, it is marked as very abusive (Gitari et al., 2015; Pedersen, 2020); (3) Training of 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 ...
    ... occurrence in the examined text (Pamungkas and Patti, 2019), or a numerical value corresponding to the number of abusive words and its level of abusiveness (Razavi et al., 2010); (2) When applying rules for classification of offensive content, the authors may decide to classify the text in a certain category ...
    ... 0 67.5 0.0 62.8 yes 28.9 20.2 24.5 0.0 24.0 81.9 27.2 Table 3: MWEs classified as yes, no, maybe and part of speech of trigger words. and other corpora previously compiled. The distribution of MWEs by part of speech categories of their trigger word is presented in Table 3. Further analysis showed ...

  • On the compatibility of lexical resources for NooJ

    Ranka Stanković, Miloš Utvić, Duško Vitas, Cvetana Krstev, Ivan Obradović (2012)
    Lexical resources for many languages are provided for the NooJ linguistic development environment. Meta-data descriptions of morphosyntactic and semantic properties of these languages and their resources are a mandatory part of each language module. In this paper we analyze how well the meta-data actually describe resources for a chosen subset of languages and to what extent are they compatible across languages to support multilingual processing. We show that there is place for improvement in both directions.
    ... the text dictionary (hraniti,V+FLX=BRANITI+Sem=cons+Prelaz=pov), although it does not exist in the *.def file. Conversely, semantic codes geo (place), etn (ethnic), ust (institution) etc. appear in the *.def file but they cannot be found in the text dictionary despite the fact that the text contains ...
    ... establish a one-to-one correspondence between the aligned segments and the original text in French. An example follows, showing the introductory chapter title and its first sentence in each of the seven languages: <text lng=”fr”>
    I Dans lequel Phileas Fogg et Passepartout s'acceptent ...
    ... par Phileas Fogg, esq., l'un des membres les plus singuliers et les plus remarqués du Reform-Club de Londres, ...

    ... <text lng=”en”>
    6 [Type text] Chapter I in which Phileas Fogg and Passepartout accept each other, the one as master, the other as man

    Mr ...

  • Using technology for knowledge transfer between academia and enterprises

    Ivan Obradović, Ranka Stanković (2014)
    ... texts an corpora. Aligned texts are pairs of texts in different languages, mainly an original and its translation, aligned on some structural level, most often the sentence. Aligned texts in LSS are in the standard, Translation Memory eXchange (TMX) format, which is XML-compliant. Corpora are large ...
    ... described in this section, and a common portal for indexing OER and other supporting TEL content throughout the network. Audio, video and written text materials from all partner institution nodes will be indexed and annotated with metadata, thus providing enhanced searching capabilities. Namely, ...

  • 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
    ... original PWN synset and words he/she has already selected for the target synset. Then, if a highlighted word found in the text in English does not have a highlighted match in the text in the target language, the lexicographer should inspect the sentence in the target language for a possible match, ...
    ... senses to all chosen words. It goes without saying that other linguistic resources, such as electronic dictionaries, bilingual word lists and corpora can be of invaluable help to the lexicographer in accomplishing this task. In this paper we present a multifunctional tool which, among ...
    ... configured to handle simultaneously up to 10 dictionaries, which can be monolingual or translational dictionaries, but also thesauri or plain corpora. Thus, VisDic went a step further as a tool which can do more than just editing and browsing wordnets. In addition to that, and contrary to the ...

  • 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 ...
    ... 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 to a custom- size collection of text files using the previously mentioned NER&Beyond web platform. story), https://zenodo.org/communities/eltec 7 SrpELTeC ...
    ... entity, so the evaluators were asked to identify and anno- tate them when they occur in text. SrpNER does not recognize WORK entity either, but these annotations were in many cases added by volunteer readers during text correction. Afterwards, students were given different no- vel chapters along with the ...
    ... distribution of different en- tity types over 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 ...

  • Building learning capacity by blending different sources of knowledge

    Ivan Obradović, Ranka Stanković, Olivera Kitanović, Dalibor Vorkapić (2016)
    ... texts and corpora. Aligned texts are pairs of texts in different languages, mainly an original and its translation, aligned on some structural level, most often the sentence. Aligned texts in BMP are in the standard, Translation Memory eXchange (TMX) format, which is XML-compliant. Corpora are large ...
    ... main features, edX offers interactive online learning software, which provides for production of multimedia educational materials, by combining text, images and videos. Exercises are also included, enabling students to check immediately their understanding of the concepts introduced by the ...

  • 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
    ... корпуса: лек- сикографске, граматичке, дијалекатске, регионалне, нестандардне, корпусе језика као нематерњег, корпусе струка (енгл. domain specific corpora) итд. У одељку 2 рада се, у општим цртама, описује лингвистичка анотација корпуса РудКор и СрпКор2013, као и могућности претраге тих корпуса по- ...
    ... „Improvements in Part-of-Speech Tagging with an Application to German”, In: Armstrong, S. et al. (eds.) Natural Language Processing Using Very Large Corpora, Dordrecht: Springer, 13–25. Miloš V. Utvić, Ranka M. Stanković, Aleksandra Đ. Tomašević, Mihailo Đ. Škorić, Biljana Đ. Lazić THE CORPUS SEARCH ...

  • A Description of Morphological Features of Serbian: a Revision using Feature System Declaration

    Cvetana Krstev, Ranka Stanković, Vitas Duško (2010)
    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 ...
    Morphology, Lexicon, lexical database, Standards for LRs
    ... français. Langue française 87. Paris: Larousse. Erjavec, T. (2004) MULTEXT-East Version 3: Multilingual Morphosyntactic Specifications, Lexicons and Corpora. In: Proc. of the Fourth Intl. Conf. on Language Resources and Evaluation, LREC'04, pp. 1535 - 1538, ELRA, Paris. Erjavec, T. MULTEXT-east mo ...

  • Developing Termbases for Expert Terminology under the TBX Standard

    http://drug.rgf.bg.ac.rs/s/repo/item-set/522 (2014)
    ... Age of Multilingual Corpora. The Journal of Specialized Translation, 18:7-29, 2012. Uwe Reinke. State of the Art in Translation Memory Technology. Translation: Computation, Corpora, Cognition, 3(1), 2013. Laurent Romary. TBX Goes TEI - Implementing a TBX Basic Extension for the Text Encoding Initiative ...
    ... translation (SMT), an approach developed at IBM in the late 1980s, now the state-of-the art paradigm in MT. The exponential growth of aligned multilingual corpora greatly improved the efficiency and accuracy of SMT in general, and many tools based on this ap- proach, such as Google Translate, are thus being more ...
    ... Developing Termbases under the TBX Standard 13 are still bound to maintain their importance in the case of expert terminology in domains where aligned corpora are sparse [10], such as, for example mining engineering or geology. In order to secure terminological consistency in one or more termbases, and to ...

  • A Tel Platform Blending Academic And Entrepreneurial Knowledge

    Ivan Obradović, Ranka Stanković, Jelena Prodanović, Olivera Kitanović (2013)
    ... platform provides electronic terminological resources, parallel (multilingual) corpora of lessons and texts in written form, and functionalities for searching and browsing of terminological resources and using them for text annotation. The contents of these resources conform to the methodic/didactic ...
    ... language support system also handles aligned texts or bitexts, pairs of semantically equivalent texts in different languages, such as an original text and its translation, that are aligned on a structural level (paragraph, sentence, phrase, etc.). Aligned texts in BAEKTEL enable better understanding ...

  • An Approach to Development of Bilingual Lexical Resources

    Stanković Ranka, Obradović Ivan, Trtovac Aleksandra (2012)
    ... of Philology, University of Belgrade. [4] Obradović, I., Stanković, R., Utvić, M. 2008. An Integrated Environment for Development of Parallel Corpora (in Serbian). In: Die Unterschiede zwischen dem Bosnischen/Bosniakischen, Kroatischen und Serbischen (pp. 563-578), B. Tošović (Ed.). Berlin: ...

  • Advancing Sentiment Analysis in Serbian Literature: A Zero and Few-Shot Learning Approach Using the Mistral Model

    Milica Ikonić Nešić, Saša Petalinkar, Mihailo Škorić, Ranka Stanković, Biljana Rujević (2024)
    Ova studija predstavlja analizu sentimenta srpskih starih romana iz perioda 1840-1920, koristeći veliki jezički model (LLM) Mistral za tehniku učenja sa zasnovani na takozvanim "zero" i "few-shot" pokušajima. Glavni pristup uvodi inovacije osmišljavanjem istraživačkih upita (promptova) uključuju tekst sa uputstvom za klasifikaciju bez primera i na osnovu nekoliko primera, omogućavajući jezičkom modelu da klasifikuje osećanja u pozitivne, negativne ili objektivne kategorije. Ova metodologija ima za cilj da pojednostavi analizu osećanja ograničavanjem odgovora, čime se povećava preciznost ...
    zero-shot, few-shot, sentiment, Serbian, Mistral model

  • WS4LR - a Worksation for Lexical Resources

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Ivan Obradović (2006)
    Lexical Resources, Wordnet, Serbian
    ... Balkan Languages, in Proc. of 1st International Wordnet Conference, Mysore, India Veronis, J. (ed.) (2000) Parallel Text processing: Alignment and Use of Translation Corpora, Dordrecht: Kluwer Academic Publishers Vossen, P. (ed.) (1998) EuroWordNet: A Multilingual Database with Lexical ...
    ... pair of semantically equivalent texts in different langauges, such as an original text and its translation, that are and aligned on a structural level (paragraph, sentence, phrase, etc.) is known as an aligned text or bitext. Aligned texts are usually constructed in two main steps: in the first ...
    ... important reason is the fact that in text recognition by Intex/Unitex the usage of all dictionaries is not always necessary, or even recommended. For example, dictionaries of English personal names transcribed according to Serbian orthography should not be applied to a text that makes no reference to such ...

  • Improving Document Retrieval in Large Domain Specific Textual Databases Using Lexical Resources

    Ranka Stanković, Cvetana Krstev, Ivan Obradović, Olivera Kitanović (2017)
    Large collections of textual documents represent an example of big data that requires the solution of three basic problems: the representation of documents, the representation of information needs and the matching of the two representations. This paper outlines the introduction of document indexing as a possible solution to document representation. Documents within a large textual database developed for geological projects in the Republic of Serbia for many years were indexed using methods developed within digital humanities: bag-of-words and named ...
    ... Surrogates can also contain an abstract and/or a snippet, a relevant text fragment. The content of a document surrogate, or its part, can be generated automatically by extracting and selecting specific terms (words) from the document text. Language processing methods and techniques devel- oped within the ...
    ... textual content of the geological project. Future plans include digitalization and full text archiving of the project content, followed by the implementation of the approach described in this paper to this future full text database. 2.2 The Initial Solution for Document Retrieval The initial solution for ...
    ... normalizing length [8]. The improved system ranking uses several measures, starting with tf idf measure based on frequencies of words allocated to the text, text length, and the document frequency [14]. Further development included modification of tf idf with cosine normalization (tfc tfc), tfc nfc term weighting ...

  • The Nooj System as Module within an Integrated Language Processing Environment

    Ranka Stanković, Duško Vitas, Cvetana Krstev (2008)
    NooJ, electronic dictionary, lexical resources
    ... information retrieval and related areas. If query is further combined with ILI, a multilingual wordnet pivot, the possibility of searching text resources (web, corpus, text) in different languages with a single query is opened. NooJ supports morphological query expansion and expansion of queries by graphs ...
    ... pair of semantically equivalent texts in different languages, such as an original text and its translation, that are aligned on a structural level (paragraph, sentence, phrase, etc.) is known as an aligned text or bitext. One of the supported formats is the Translation Memory eXchange format ...
    ... resources management 4.1. Parallel Text Management The WS4LR module for management of aligned parallel texts uses texts which have previously been aligned using Xalign as an alignment tool (Bonhomme 2001). Parallel texts which usually originate from a text in one language and its translation ...