Претрага

Упит dcterms_subject_txt:morphological dictionaries

96 items

  • Речник САНУ као база терминолошких речника (на примеру речника кулинарства)

    Рада Стијовић, Олга Сабо, Ранка Станковић (2017)
    ... Evaluation Conference (LREC), 23-28 May 2016, Portorož. 7. Ranka Stanković, Ivan Obradović, Cvetana Krstev, Duško Vitas, “Production of morphological dictionaries of multi-word units using a multipurpose tool”, In: Proceedings of the Computational Linguistics-Applications Conference, 2011. 8. Милош ...
    ... As a starting point, we used a digitized version of the Great Serbian chef Katarina Popovic Midžine (processed using Unitex tool and morphological dictionaries for Serbian language in DELA format). After this we applied Leximir tool to extract a list of the lemma frequencies in the cookbook, ...
    ... ИНФОтека 12, бр. 2 (децембар 2011): 39-51. 9. Staša Vujičić Stanković, Cvetana Krstev, Duško Vitas, “Enriching Serbian WordNet and Electronic Dictionaries with Terms from the Culinary Domain”, In The Proceedings of Seventh Global WordNet Conference 2014. 10. Jurafsky, D. (2014). The Language of ...

  • Using Lexical Resources for Irony and Sarcasm Classification

    Miljana Mladenović, Cvetana Krstev, Jelena Mitrović, Ranka Stanković (2017)
    The paper presents a language dependent model for classification of statements into ironic and non-ironic. The model uses various language resources: morphological dictionaries, sentiment lexicon, lexicon of markers and a WordNet based ontology. This approach uses various features: antonymous pairs obtained using the reasoning rules over the Serbian WordNet ontology (R), antonymous pairs in which one member has positive sentiment polarity (PPR), polarity of positive sentiment words (PSP), ordered sequence of sentiment tags (OSA), Part-of-Speech tags of words (POS) ...
    ... presents a language dependent model for classification of statements into ironic and non-ironic. The model uses various language resources: morphological dictionaries, sentiment lexicon, lexicon of markers and a WordNet based ontology. This approach uses various features: antonymous pairs obtained using ...
    ... the following way (step 1 in Fig 1). First we manually marked each tweet with a (BCMS) or (not_BCMS) mark. After that we used Serbian Morphological Electronic Dictionaries [22] to automatically tag each word with a mark of belonging to a language _word or not belonging _not (resource A in Fig 1). We introduced ...
    ... illustrates all three sources of problems (underlined words). Namely, these words cannot be recognized as words from BCMS as they were not found in dictionaries, and as a consequence the tweet was rejected. An example of a false positive tweet is a tweet in Slovenian Zakaj smo se pa borili, a za to, da ...

  • Bridging Computational Lexicography and Corpus Linguistics: A Query Extension for OntoLex-FrAC

    Christian Chiarcos, Ranka Stanković, Maxim Ionov, Gilles Sérasset (2024)
    OntoLex, dominantni standard zajednice za mašinski čitljive leksičke resurse u kontekstu RDF-a, Linked Data i tehnologija Semantičkog veba, trenutno se proširuje sa posebnim modulom za Frekvencije, Primere i Informacije zasnovane na Korpusu (OntoLex-FrAC). Predlažemo novi komponent za OntoLex-FrAC, koji se bavi inkorporacijom korpusnih upita za (a) povezivanje rečnika sa korpusnim mašinama, (b) omogućavanje RDF baziranih web servisa da dinamički razmenjuju korpusne upite i podatke odgovora, i (c) korišćenje konvencionalnih upitačkih jezika za formalizaciju unutrašnje strukture kolokacija, skica reči i ...
    standardizacija, digitalna leksikografija, OntoLex, upiti korpusa, povezani podaci, Lingvistički povezani otvoreni podaci

  • SrpELTeC: A Serbian Literary Corpus for Distant Reading

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

  • Development and Evaluation of Three Named Entity Recognition Systems for Serbian - The Case of Personal Names

    Branislava Šandrih, Cvetana Krstev, Ranka Stanković (2019)
    In this paper we present a rule- and lexicon-based system for the recognition of Named Entities (NE) in Serbian news paper texts that was used to prepare a gold standard annotated with personal names. It was further used to prepare training sets for four different levels of annota tion, which were further used to train two Named Entity Recognition (NER) sys tems: Stanford and spaCy. All obtained models, together with a rule- and lexicon based system were evaluated on ...
    NER, Named Entity Recognition Systems, Serbian, Personal Names
    ... Maurel, 2004; Mau- rel et al., 2011). Each transducer rely in its work on the results of previous transducers and on e- dictionaries of Serbian (Vitas and Krstev, 2012). E-dictionaries play an important role specifically in the recognition of name expressions, since, beside general lexica, they contain ...
    ... NE classes (or- ganization names) and new sub-classes (e.g. for geopolitical names: regions, super-regions and city counties). In addition, the e-dictionaries of Serbian were also continually improved and en- hanced, and that by itself contributes to better per- formance of SRPNER. The new version of ...
    ... which yielded “four levels” of gold standard. Between these repeated runs the devel- opment of SRPNER continued, as well as the en- hancement of e-dictionaries of Serbian. 3 Training Different NER Systems 3.1 Training Sets The gold standard GOLDPERS contains 9, 046 sentences, each one enclosed in ...

  • Увођење доменских и семантичких маркера за област рударства у српске електронске речнике

    Иван Обрадовић, Александра Томашевић, Ранка Станковић, Биљана Лазић (2017)
    ... Ranka Stanković, Bilјana Lazić INTRODUCING DOMAIN AND SEMANTIC MARKERS FOR THE FIELD OF MINING IN SERBIAN ELECTRONIC DICTIONARIES Summary Semantic markers in electronic dictionaries allow for complex queries for information extrac- tion. When it comes to domain-specific queries, the availablese to ...
    ... Speech and Lan- guage Processing, Draft of November 7, 2016. Крстев 2008: Cvetana Krstev, Processing of Serbian – Automata, Texts and Elec- tronic dictionaries Faculty of Philology, University of Belgrade, Belgrade. Крстев и др., 2008: Cvetana Krstev, DuškoVitas, Gordana Pavlović-Lažetić, “Re- sources ...

  • A Twitter Corpus and Lexicon for Abusive Speech Detection in Serbian

    Danka Jokić, Ranka Stanković, Cvetana Krstev, Branislava Šandrih (2021)
    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 ...
    uvredljivi jezik, govor mržnje, srpski, tviter, leksikon, korpus
    ... lexicon of offensive words are lists of swear words, curses, abusive expressions, existing general dictionaries, slang dictionaries, surveys and contributions through crowd- sourcing, translation of dictionaries and lexicons from other languages, lexicons of sentiment words and expressions, rhetorical figures ...
    ... on attacks and improper behaviour that are the result of national, racial, or religious hatred and intolerance. The system relied on electronic dictionaries of Serbian and local grammars that covered various patterns of hate speech and ways they were covered in newspaper articles. It should be noted ...
    ... word can be used to refer to immoral or criminal 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 ...

  • A Tel Platform Blending Academic And Entrepreneurial Knowledge

    Ivan Obradović, Ranka Stanković, Jelena Prodanović, Olivera Kitanović (2013)
    ... and textual resources (Fig 2). One of the basic lexical resources is the system of morphological dictionaries of Serbian simple words and compounds in the so-called LADL format [8]. Morphological dictionaries in the same format exist for many other languages, including French, English, Greek ...
    ... Web services, and knowledge management. Wiley. com. [10] Stanković, R., Obradović, I., Krstev, C., & Vitas, D. (2011). Production of morphological dictionaries of multi-word units using a multipurpose tool. In Proceedings of the Computational Linguistics- Applications Conference, CLA '11 (pp ...
    ... query. Using the available resources, the system can expand the query morphologically, which is especially important for Serbian, due to its morphological richness. The query can also be expanded to another language thus supporting multilinguality within BAEKTEL. The BAEKTEL language support ...

  • 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

  • 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
    ... available. Column POS shows the PWN synset POS, while the last column SrpPOS shows the POS for the Serbian equivalent, obtained from Serbian morphological dictionaries (Krstev et al., 2010), if this term was found in the dictionary. Definition in English DefEn is intended to help the expert in correcting ...
    ... automatically adapted Serbian synsets. We also plan to include further restrictions using semantic and domain markers from Serbian Serbian morphological dictionaries and other resources, in order to improve precision of system. Proceedings of CLIB 2018 112 Acknowledgements This research was partially ...
    ... alignment with EWN. Bentivogli and Pianta (2003) proposed a method for extending MultiWordNet1 with phrases, by extracting them from bilingual dictionaries and corpora with techniques similar to those used for collocation extraction. In (Bhingardive et al., 2014) a method for Sanskrit WordNet extension ...

  • 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 ...
    ... novels, retrieval of hard co- pies, scanning, OCR, automatic correction of OCR errors (for which a specialized tool ba- sed on the Serbian morphological dictionaries was produced (Krstev and Stanković, 2020)), correction of remaining errors by a number of volunteer readers, and production of metadata. ...
    ... conclusions and plans for the future work were stated in Section 6. 2 Related Work The existence of large-scale lexical resources for Serbian, e-dictionaries in particular (Kr- stev, 2008), coupled with local grammars in the form of finite-state transducers (Vitas and Krstev, 2012), enabled the development ...
    ... XML-TEI tags used to preserve the format of original editions. Authors’ solution was based on the cascades of finite-state automata and both general dictionaries and those built speci- fically for the project. The evaluation showed that the slot error rate of name tagging was 6.1%. A dataset of literary entities ...

  • Дигиталне библиотеке у рударству и геологији са посебним освртом на представљање сиве литературе

    Биљана Лазић, Александра Томашевић, Михаило Шкорић (2019)
    Имајући у виду потребу за проналажењем информација похрањених у различитим облицима документације која се генерише у областима рударства и геологије на Рударско-геолошком факултету Универзитета у Београду, отпочет је процес развоја дигиталне библиотеке ROmeka@RGF, на платформи за приказивање дигиталних колекција - Омека. Значајан део документације представља такозвана сива литература која је претежно заступљена у виду вишетомне документацијe. Први савладани изазов представљало је повезивање различитих вишетомних делова пројектних извештаја у једну целину која би била лако доступна и претражива.
    дигиталне библиотеке, сива литература, Омека, језички ресурси, речници
    ... given to relational dictionaries which are designed to define document relations. We will also present some language resources for Serbian language which are used to improve information retrieval. Keywords: digital libraries, grey literature, Omeka, language resources, dictionaries. ...

  • Developing Termbases for Expert Terminology under the TBX Standard

    http://drug.rgf.bg.ac.rs/s/repo/item-set/522 (2014)
    ... system of morphological dictionaries for Serbian, both of sim- ple and compound words has been developed over a very long period, follows the so-called DELA format [8]. The DELAS dictionaries of simple words have reached a very high level of coverage of Serbian, while the DELAC dictionaries of compounds ...
    ... TMX with morphological information using Serbian electronic morphological dictio- naries and a web service developed by HLT Group from University of Belgrade. There is still much work to be done in this area, in the first place an en- hancement of domain specific morphological dictionaries of terminology ...
    ... processing of all texts, such as lematization, morphological analysis, named entity recognition and the like. This is especially important in the case of domain specific texts as in the fields of geology or mining. Thus, appropriate electronic morphological dictionaries are ❉❡✈❡❧♦♣✐♥❣ ❚❡r♠❜❛s❡s ✉♥❞❡r t❤❡ ...

  • Proširivanje upita zasnovano na leksičkim resursima

    Ranka Stanković, Ivan Obradović, Cvetana Krstev (2009)
    U radu je opisano kako se leksički resursi za srpski jezik i softverski alati, razvijeni u okviru Grupe za jezičke tehnologije Univerziteta u Beogradu, mogu koristiti za unapređenje postavljanja upita. Rezultati pretrage mogu biti značajno unapređeni korišćenjem različitih leksičkih resursa, kakvi su morfološki rečnici i semantičke mreže. Izloženi pristup može se iskoristiti i u Sistemu naučnih, tehnoloških i poslovnih informacija, jer je efikasno pretraživanje ovog dragocenog resursa, imajući u vidu njegovu heterogenost i obim, kao i preovladavajući tekstualni sadržaj, ...
    ... Belgrade can be used for improvement of queries. Search results can be substantially improved by using various lexical resources, such as morphological dictionaries and semantic networks. The outlined approach may be used within the System of scientific, technical and business information. Efficient ...

  • Keyword Extraction from Parallel Abstracts of Scientific Publications

    Slobodan Beliga, Olivera Kitanović, Ranka Stanković, Sanda Martinčić-Ipšić (2017)
    ... and (2) a Serbian lemmatizer. For lemmatization, we use Serbian morphological elec- tronic dictionaries and grammars developed within the University of Bel- grade Human Language Technology Group [17]. Morphological electronic dictionaries of Serbian for NLP have been developing for many years now. In ...
    ... tasks. Serbian e-dictionaries of simple forms have reached a con- siderable size: they have more than 140,000 lemmas generating more than 5 million forms and 18,000 multi-word lemmas [18]. Different approaches (stemming and lemmatization) were caused by the dif- ferences in morphological feature of these ...

  • Глаголи у кухињи и за столом

    Цветана Крстев, Биљана Лазић (2015)
    У раду је приказано истраживање лексике на српском језику кулинарског домена које се заснива на коришћењу доменског корпуса, електронских лексичких ресурса, пре свега WordNet-а и морфолошких речника, и локалних граматика. Приказане су доменске специфичности ових ресурса, како се користе, и међусобно употпуњују. Посебно је приказано како се коришћењем доменског корпуса могу екстраховати глаголи специфични за кулинарски домен и описати начини њиховог коришћења. Дат је попис глагола са основним подацима који је добијен применом представљених метода.
    аутоматска обрада, коначни трансдуктори, електронски речници, семантичке мреже, локалне граматике, кулинарство
    ... центар, Београд. 3. ВУЈИЧИЋ СТАНКОВИЋ И ДР. 2014: Staša Vujičić Stanković, Cvetana Krstev, Duško Vitas, “Enriching Serbian WordNet and Electronic Dictionaries with Terms from the Culinary Domain”, In The Proceedings of Seventh Global WordNet Conference 2014, eds. Heili Orav, Christiane Fellbaume, ...
    ... Applications-2. Springer Berlin Heidelberg, 121-162. 8. КРСТЕВ 2008: Cvetana Krstev, Processing of Serbian – Automata, Texts and Electronic dictionaries. Belgrade: Faculty of Philology, University of Belgrade. 9. КРСТЕВ И ДР. 2014: Cvetana Krstev, Staša Vujičić Stanković, Duško Vitas, “Approximate ...
    ... of the lexica of the culinary domain in Serbian based on the use of the domain corpus, electronic lexical resources – WordNet and morphologcila dictionaries – and local grammars. We presented the domain characteristics of these resources, how they can be used for research and for mutal enrichment. ...

  • Towards Semantic Interoperability: Parallel Corpora as Linked Data Incorporating Named Entity Linking

    Ranka Stanković, Milica Ikonić Nešić, Olja Perisic, Mihailo Škorić, Olivera Kitanović (2024)
    U radu se prikazuju rezultati istraživanja vezanih za pripremu paralelnih korpusa, fokusirajući se na transformaciju u RDF grafove koristeći NLP Interchange Format (NIF) za lingvističku anotaciju. Pružamo pregled paralelnog korpusa koji je korišćen u ovom studijskom slučaju, kao i proces označavanja delova govora, lematizacije i prepoznavanja imenovanih entiteta (NER). Zatim opisujemo povezivanje imenovanih entiteta (NEL), konverziju podataka u RDF, i uključivanje NIF anotacija. Proizvedene NIF datoteke su evaluirane kroz istraživanje triplestore-a korišćenjem SPARQL upita. Na kraju, razmatra se povezivanje Linked ...
    paralelni korpusi, povezivanje imenovanih entiteta, prepoznavanje imenovanih entiteta, NER, NEL, povezani podaci, NIF, Vikipodaci

  • Towards a Mining Equipment Ontology

    Ranka Stanković, Ivan Obradović, Olivera Kitanović, Ljiljana Kolonja (2012)
    ... of terminological resource in corresponding sub-fields, often in the form of controlled dictionaries, which are consistent collections of terms selected for a specific purpose. For example, controlled dictionaries can be derived from RudOnto for the area of Geostatistics, Mine safety, Mineral resource ...

  • Using Query Expansion for Cross-Lingual Mathematical Terminology Extraction

    Velislava Stoykova, Ranka Stanković (2018)

  • Integracija heterogenih tekstualnih resursa

    Ranka Stanković, Ivan Obradović (2007)
    U radu je opisan pristup integraciji heterogenih tekstualnih resursa za srpski jezik uz pomoć jednog kompleksnog softverskog alata, razvijenog specijalno za ove potrebe. Opisani su struktura i osnovne komponente razvijenog sistema. Iznete su i mogućnosti unapređivanja resursa međusobnom razmenom informacija, koje pruža razvijeno integrisano okruženje. Konačno, opisana je i mogućnost primene integrisanih heterogenih resursa za proširenje upita, kao i pretraživanje tekstova uopšte, a naznačeni su i neki od pravaca daljeg razvoja.
    ... WS4LR (WorkStation for Lexical Resources), which synchronously handles corpora of Serbian, multilingual aligned corpora, a system of morphological dictionaries for Serbian, the Serbian wordnet and the multilingual ontology of proper names Prolex. We describe the possibilities WS4LR offers for ...
    ... important feature which opens new possibilities for processing of texts, namely resource combining, in particular the combining of morphological information from the dictionaries and semantic information from the wordnet. Finally, we explain how integrated heterogeneous resources can be used for query expansion ...