Претрага

Упит dcterms_subject_txt:finite-state transducers

49 items

  • Softverski alati za korišćenje resursa za srpski jezik

    Ivan Obradović, Ranka Stanković (2008)
    ... Languages: The Fifth Conference, Leipzig 2003, Zy- batow, Gerhild et al. (eds.), Peter Lang: Frankfurt am Main, pp. 3-17. Mohri, M. (1997) “Finite-state transducers in language and speech processing”, Computational Linguistics, vol. 23 , no. 2, pp. 269 – 311. IVAN OBRADOVIć, RANKA STANKOVIć 57a ...
    ... would enable local usage of some WS4LR functions, with the possibility of access to the WS4QE web application is also be- ing considered. 1On finite transducers see e.g. Mohri, 1997. 2http://igm.univ-mlv.fr/~unitex/ 3http://www.nooj4nlp.net 4Let us remind that “cx” represents the letter ć in the Au- rora ...
    ... compound processing Finally, the module for management of dic- tionaries enables the activation of the editor of regular expressions, that is, transducers that de- scribe the inflectional characteristics of the cho- sen lemma or class. This completes the set of tools the user needs in order to be ...

  • Аnaliza mogućnosti povećanja nagiba završne kosine površinskog kopa “Podbraćan”

    Vladimir Čebašek, Veljko Rupar (2018)
    Eksploatacijom boksita iz ležišta "Podbraćan" formiran je površinski kop sa maksimalnom visinom zavšne kosine od 280 m. Redovnom kontrolom stabilnosti trenutnog stanja kosina površinskog kopa utvrđeno je da faktor sigurnosti iznosi Fs = 1.71 – 1.85, a što je ukazalo da postoji mogućnost povećanja nagiba kosine. U radu je prikazan postupak analize mogućnosti povećanja nagiba završne kosine površinskog kopa "Podbraćan".
    stabilnost kosina, povećanje nagiba kosina, metoda konačnih elemenata

  • A bilingual digital library for academic and entrepreneurial knowledge management

    Ranka Stanković, Cvetana Krstev, Biljana Lazić, Dalibor Vorkapić (2015)
    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 ...
    Knowledge management, Digital library, Multilingualism, Language Resources, Terminology
    ... morphology, need corresponding language resources in the form of morphological e-dictionaries and grammars, implemented by finite state automata, finite state transducers and multi-word unit inflection rules (Krstev, 2008). All of them are used to improve the full-text search performance of our ...
    ... query for further morphological expansion, based on morphological e-dictionaries, the system of rules for multi-word inflection, and finite automata and transducers (Krstev et al, 2008; Krstev 2008). An example of query expansion will be presented in section 5.1. Metadata is assigned to each article ...

  • 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
    ... designed in a form of the cas- cades of Finite-State Transducers (FST) in which every transducer recognizes and tags a certain class of NEs (Friburger and 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 ...
    ... https://github.com/fyh828/gemini/ 1068 1. Association for Computational Linguistics, pages 141–150. Nathalie Friburger and Denis Maurel. 2004. Finite- state Transducer Cascades to Extract Named Entities in Texts. Theoretical Computer Science 313(1):93– 104. Ralph Grishman and Beth Sundheim. 1996. Message ...
    ... 2002). The ML-based methods can often be “black boxes”, in compar- ison with RB techniques which are easy to in- terpret. Yet, ML-based methods are state-of-the- art. Such example is a Stanford Named Entity Recognizer (Manning et al., 2014), which can be trained for many languages. Other notable NER platforms ...

  • Understanding the effect of synthesis and sintering temperature on the functional properties of barium titanate/cobalt ferrite composites

    Marija Šuljagić, Aleksandar Kremenović, Ivan Petronijević, Adis Džunuzović, Miljana Mirković, Vladimir Pavlović, Ljubica Anđelković (2023)
    To investigate the effect of synthesis procedure and sintering temperature on the functional properties of perovskite/spinel ceramics, BaTiO3/CoFe2O4 composites were prepared by thermal decomposition, coprecipitation, and microemulsion method, and sintered at 1150°C and 1300°C. The phase composition and morphology of as-prepared powders as well as sintered ceramics were thoroughly examined by X-ray powder diffraction (XRPD) and scanning electron microscopy (SEM) coupled with electron dispersive spectroscopy (EDS). The dielectric and ferroelectric measurements were performed in detail. Generally, the ...
    Perovskite/spinel ceramics, Multiferroic, Sintering, Influence of synthesis method

  • Vebran Web Services for Corpus Query Expansion

    Ranka Stanković, Miloš Utvić (2020)
    U ovom radu se govori o razvoju veb usluga Vebran i njihovoj primeni u poboljšanju pretraživanja korpusa. Veb-servisi Vebran koriste se za konsultovanje spoljnih leksičkih izvora za srpski jezik (uglavnom elektronski morfološki rečnici i srpski Vordnet) i proširivanje korisničkih upita radi dobijanja relevantnijih rezultata iz srpskih korpusa.
    corpus search, web service, Serbian lexical resources, query expansion
    ... code. Every inflectional class code is associated with a corresponding finite-state transducer responsible for the generation of all inflectional forms of DELAS lemma. Thus, the DELAS-type dictionary with finite-state transducers for inflection enables the production of a DELAF- type dictionary which ...
    ... technology, allowing users to 1) Compile rules and dictionaries as finite-state machines; 2) Use variables instanced with a part of the text or with any characters; 3) Use regular expressions and graphs of automata and transducers for searching and extraction; and 4) Build cascades of rules. Corpora ...

  • Human factor risk management procedures applied in the case of open pit mine

    Snežana Kirin, Aleksandar Sedmak, Wei Li, Miodrag Brzaković, Igor Miljanović, Ana Petrović, Simon Sedmak (2021)
    Risk management aims to provide a controlled work environment to ensure the safe operation of the high-risk systems. It is a dynamic process which work in a continual state of change. The issue of human factor risk and rules and regulations in open pit mine is a main focus of this paper in order to develop predictive models of behavior of workers in relation to compliance with the procedures and rules. Presented survey was conducted in open pit coal ...
    Upravljanje rizikom, ljudski faktor, bager sa kašikom, metod konačnih elemenata

  • 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
    ... categories gender and animacy are fixed. For the purpose, this description is sufficient because the inflectional process is governed by inflectional transducers. (c) The Elag subsystem of Unitex for resolving ambiguities uses much more elaborated morphosyntactic description. Its description of ‘paukal’ ...

  • 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, ...
    ... Bucureşti, Publishing house of the Romanian academy. [3] Vitas D., Krstev C. (2007), „Extending Serbian E dictionary by the Use of the Lexical Transducers“, Proc. of the 6th and 7th INTEX/Nooj Workshop, S. Koeva, D. Maurel, M. Silberztein (eds.), Formaliser les langues avec l'ordinateur: De INTEX ...

  • A Tel Platform Blending Academic And Entrepreneurial Knowledge

    Ivan Obradović, Ranka Stanković, Jelena Prodanović, Olivera Kitanović (2013)
    ... 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 ...
    ... enterprises through blending of academic and entrepreneurial knowledge by means of OER. This enables life-long learners from enterprises to access state of the art education and high quality courses for their continuing development in a way that is more flexible to combine with professional activities ...

  • Improvement of geodatabase queries within GeolISS

    Ranka Stanković (2008)
    ... lexical resources over a long period, the resources reaching a considerable volume to date [8]. They include morphological e-dictionaries and finite state transducers, which offer the possibilities for solving the problem of flections in queries, and electronic thesauri, ontologies and wordnets which ...

  • Managing mining project documentation using human language technology

    Aleksandra Tomašević, Ranka Stanković, Miloš Utvić, Ivan Obradović, Božo Kolonja (2018)
    Purpose: This paper aims to develop a system, which would enable efficient management and exploitation of documentation in electronic form, related to mining projects, with information retrieval and information extraction (IE) features, using various language resources and natural language processing. Design/methodology/approach: The system is designed to integrate textual, lexical, semantic and terminological resources, enabling advanced document search and extraction of information. These resources are integrated with a set of Web services and applications, for different user profiles and use-cases. Findings: The ...
    Digital libraries, Information retrieval, Data mining, Human language technologies, Project documentation

  • Bilingual lexical extraction based on word alignment for improving corpus search

    Jelena Andonovski, Branislava Šandrih, Olivera Kitanović (2019)
    Library and Information Sciences,Computer Science Applications

  • Towards translation of educational resources using GIZA++

    Ivan Obradović, Dalibor Vorkapić, Ranka Stanković, Nikola Vulović, Miladin Kotorčević (2016)
    ... software with support for DTD (Document Type Definition) scheme validation and well- formedness check. This part can be automated using finite- state transducers, but manual intervention is still necessary. The next key step is aligning the text – parallelization. The aim is to determine for each ...
    ... special service that requires specific subject- matter expertise and high technical skills from everyone involved. This paper presents the current state of research in course translation. The translation of electronic courses is an ongoing activity at the University of Belgrade Faculty of Mining and ...

  • Combining Heterogeneous Lexical Resources

    Cvetana Krstev, Duško Vitas, Ranka Stanković, Ivan Obradović, Gordana Pavlović-Lažetić (2004)
    development of lexical resources, morphological dictionaries, WordNet
    ... example (2), the adjective devojcyin is the possessive adjective of the noun devojka. This information in the DELAS dictionary can be used by finite transducers to lemmatize the text using any lemma, arbitrarily chosen, from the derivational nest. • The Serbian wordnet (SWN) is being developed ...
    ... dictionary of simple lemmas, a dictionary of compounds (under construction), the corresponding dictionaries of word forms, and morphological finite-state automata that model certain classes of lemmas. The current size of SMD of simple lemmas is around 65.000, and they produce a dictionary of ...
    ... is the part of speech (PoS) and the code of the inflectional class (for inflectional lemmas). Every inflectional class is implemented as a finite state transducer that is used to produce the dictionary of simple word forms (DELA F). Optional morphosyntactic, semantic and information on dialect ...

  • A Tool for Enhanced Search of Multilingual Digital Libraries of E-journals

    Ranka Stanković, Cvetana Krstev, Ivan Obradović, Aleksandra Trtovac, Miloš Utvić (2012)
    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 ...
    multilingual digital libraries, query expansion, TMX
    ... several other lexical resources, such as morphological e-dictionaries. Together with the system of rules for compound inflection, finite automata and transducers, these dictionaries represent the basis for morphological expansion of queries. As for semantic and bilingual expansion, the system ...

  • E-Connecting Balkan Languages

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Svetla Koeva (2009)
    In this paper we present a versatile language processing tool that can be successfully used for many Balkan languages. This tool relies for its work on several sophisticated textual and lexical resources that were developed for most of Balkan languages. These resources are based on several de facto standards in natural language processing.
    Query expansion, e-dictionary, wordnet, proper name, aligned text
    ... production of a DELAF-type dictionary which consists of all inflectional forms with their grammatical information. In Unitex environment one finite-state transducer responsible for generation of all inflectional forms of each DELAS lemma corresponds to each inflectional class code. The Serbian ...
    ... checked. Morphological expansion is performed by Unitex modules that use morphological dictionaries of simple words as well as inflectional transducers. This options works only if a particular query keyword is listed in the morphological dictionary of the corresponding language. If it is not ...

  • Medical Domain Document Classification via Extraction of Taxonomy Concepts from MeSH Ontology

    Mihailo Škorić, Mauro Dragoni (2019)
    This paper is a result of a task that was presented to attendants of Keyword Search in Big Linked Data summer school, that was organized by Vienna University of Technology, under the Keystone COST action in the summer of 2017. It presents a specific approach to the classification via creation of minimal document surrogates based on the US National medical library’s MeSH ontology, which is derived from the Medical Subject Headings thesaurus. In a series of previously classified medically ...
    document classification, MeSH, ontology, information extraction
    ... Replace("Muscles", "A10.690"); Figure 7. The section of a find and replace script based on the previously generated CSV file (Figure 6). finite state machines and transducers to solve this problem, which is more complex to implement but performs faster in processing this type. Transformation of documents ...

  • Definisanje parametara čvrstoće na smicanje kod izvođenja kosina u ispucalom stenskom masivu

    Zoran M. Berisavljević (2016-04-01)
    Definisanje parametara čvrstoće na smicanje ispucalih stenskih masa predstavlja jedanod najzahtevnijih zadataka mehanike stena. Geotehnička istraživanja su uglavnomograničena na rezultate laboratorijskih ispitivanja malih makroskopski homogenihuzoraka, sa kojih se vrši ekstrapolacija rezultata na terensku razmeru. Ispitivanja semogu vršiti in situ, ali su i ona ograničena veličinom korišćene aparature imikrolokacijom na kojoj se vrše ispitivanja. Pored toga, moguće je vršiti različitaispitivanja na fizičkim modelima, koja su veoma složena i skupa. Ekstrapolacijapodataka sa malog uzorka na terensku razmeru daje mnogo bolje rezultate ...
    naponsko stanje, ispucalost, heterogenost, čvrstoća na smicanje, geološki indeksčvrstoće, Hoek-Brownov materijal, kompozitni uzorci, dezintegracija, povratna analiza

  • Using technology for knowledge transfer between academia and enterprises

    Ivan Obradović, Ranka Stanković (2014)
    ... grammar need corresponding language resources in the form of grammars. Grammars within LSS are implemented by the so called finite state automata, finite state transducers and compound inflection rules (Krstev, 2008). The language support system handles various types of requests issued by the tools ...
    ... insight into expert knowledge gained through practice within enterprises, whereas employees involved in life-long learning will have access to state of the art high quality academic courses and thus continue with their professional development in a way more suitable to their professional activities ...
    ... ve solution enabling mobile learning that is accessible from anywhere, at any time, by means of virtually any PC or mobile device. It features state of the art content authoring tools, as well as tools for measuring real-time engagement in virtual classes and tracking individual student progress ...