Претрага

Упит dcterms_subject_txt:word alignment

54 items

  • An Approach to Efficient Processing of Multi-Word Units

    Cvetana Krstev, Ivan Obradović, Ranka Stanković, Duško Vitas (2013)
    Efficient processing of Multi-Word Units in the course of development of morphological MWU dictionaries is not easy to achieve, especially when languages with complex morphological structures are concerned, such as Serbian. Manual development of this type of dictionaries is a tedious and extremely slow process. To alleviate this problem we turned to our multipurpose software tool, dubbed LeXimir, in the production of lemmas for e-dictionaries of multi-word units. In addition to that, we developed a procedure aimed at making ...
    Natural Language Processing, Grammatical Category, Lexical Representation, MWU, multi-word unit
    ... Efficient Processing of Multi-Word Units 9 • Noun/noun (both inflect and agree in number and case) • Noun/noun in the genitive or in the instrumental (only the first noun inflects) • Word/noun (only the second noun inflects; the first word is usually not a Serbian simple word) • Noun/adjective (both ...
    ... CflxGroup="NC_AXN"> <Word ID="1" POS="A" Flex="true" Case="1" Anim="$a" Gen="$g"/> <Word ID="2" POS="N" Flex="true" Case="1" Anim="=$a" Gen="=$g"/> <Word ID="1" Num="s" Cond="$PRE"/> <Word ID="2" Num="s"/> ...
    ... d> <Word ID="1" Case="1" Num="p"/> <Word ID="2" Case="1" Num="p"/> <Word ID="1" Case="1" Num="s"/> <Word ID="2" Case="1" Num="s" SinSem="+VN,+Coll,+HumColl"/> ...

  • Production of morphological dictionaries of multi-word units using a multipurpose tool

    Ranka Stanković, Ivan Obradović, Cvetana Krstev, Duško Vitas (2011)
    The development of a comprehensive morphological dictionary of multi-word units for Serbian is a very demanding task, due to the complexity of Serbian morphology. Manual production of such a dictionary proved to be extremely time-consuming. In this paper we present a procedure that automatically produces dictionary lemmas for a given list of multi-word units. To accomplish this task the procedure relies on data in e-dictionaries of Serbian simple words, which are already well developed. We also offer an evaluation ...
    electronic dictionary, Serbian, morphology, inflection, multi-word units, noun phrases, query expansion
    ... ‘$PRE ’ /> <Word ID = ‘2 ’ Num= ‘ s ’ /> <Word ID = ‘1 ’ Case = ‘1 ’ Num= ‘p ’ /> <Word ID= ‘2 ’ Case = ‘1 ’ Num= ‘ p ’ /> <Word ID = ‘1 ’ Case ...
    ... (both inflect and agree in number and case) • Noun/noun in the genitive (only the first noun inflects) • Word/noun (only the second noun inflects; the first word is usually not a Serbian simple word) • Noun/adjective (both inflect and agree in gender, number and case) However, there are 25 different ...
    ... AXN’> <Word ID = ‘1 ’ POS= ‘A’ F l ex = ‘ t r u e ’ Case = ‘1 ’ Anim= ‘$ a ’ Gen= ‘$ g ’ /> <Word ID = ‘2 ’ POS= ‘N’ F l ex = ‘ t r u e ’ Case = ‘1 ’ Anim= ‘=$ a ’ Gen= ‘=$g /> <Word ID= ‘1 ’ Num= ‘ s ’ Cond ...

  • Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian

    Ranka Stanković, Branislava Šandrih, Cvetana Krstev, Miloš Utvić, Mihailo Škorić (2020)
    The training of new tagger models for Serbian is primarily motivated by the enhancement of the existing tagset with the grammatical category of a gender. The harmonization of resources that were manually annotated within different projects over a long period of time was an important task, enabled by the development of tools that support partial automation. The supporting tools take into account different taggers and tagsets. This paper focuses on TreeTagger and spaCy taggers, and the annotation schema alignment ...
    Part-of-Speech tagging, lemmatization, corpus, evaluation, Serbian, morphological dictionary
    ... sentence. Each line contains the following ten fields, separated with tabulator character: 1) word index (integer starting from 1 for each new sentence), 2) word form or punctuation symbol, 3) lemma or stem of word form, 4) Universal Part-of-Speech tag, 5) language-specific tag with nPOS introduced in ...
    ... supporting tools take into account different taggers and tagsets. This paper focuses on TreeTagger and spaCy taggers, and the annotation schema alignment between Serbian morphological dictionaries, MULTEXT-East and Universal Part-of-Speech tagset. The trained models will be used to publish the new ...
    ... prepara- tion of training sets to be used for different taggers and tagsets in the future. The research was focused on anno- tation schemata alignment between Serbian morphological dictionaries tagset (presented briefly in Subsection 2.1.), MULTEXT-East tagset (Erjavec, 2012), and the Universal ...

  • 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.
    ... were in XML format in compliance with TEI, and their alignment was performed at the sentence level using the ACIDE system (Obradović et al 2008), which can handle aligned texts in various formats (TEI, TMX, html, Vanilla). During the alignment process, the texts were segmented in such a way as ...

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

    Ranka Stanković, Duško Vitas, Cvetana Krstev (2008)
    NooJ, electronic dictionary, lexical resources
    ... al dictionaries, namely the wordnet hierarchy can be used to add semantic information to word entries in morphological dictionaries. Some basic semantic information has already been attached to simple word entries, such as +Hum (human) and +Bot (botanic) for nouns, and +Col (colour) and +Mat ...
    ... already being developed with query expansion functionality. The integration with MS Word would be very useful for numerous users, and to that end we plan to incorporate some of WS4LR functions into MS Word as well. 6. References Bilotti, M., Query Expansion Techniques for Question Answering ...
    ... and its relations. This adds additional functionality for information retrieval, indexing, machine aided translation, machine translation, and alignment of multilingual texts. WS4LR handles aligned texts as well. A pair of semantically equivalent texts in different languages, such as an original ...

  • 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
    ... checks on wordnets. For example, when word senses are in question, WS4LR provides information of the senses that have already been used for a word, so the user can assign a sense tag that has not previously been assigned, thus preventing duplicate word-sense pairs. The wordnet module can also ...
    ... preferably usage examples. As synset elements appear as a word-sense pairs the lexicographer has to assign 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 lex ...
    ... in cases of aligned multilingual wordnets, such as EuroWordNet and BalkaNet, since a common conceptual network substantially alleviated the alignment. However, within the BalkaNet project the following questions have often been raised: are concepts linguistically independent or not, are the ...

  • 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
    ... projects ON-178006 and III 47003. References Andonovski, Jelena, Branislava Šandrih and Olivera Kitanović. “Bilingual Lexical Extraction based on Word Alignment for Improving Corpus Search”. The Electronic Library Vol. 37, no. 2 (2019): 722-739 Evert, Stefan and The OCWB Development Team. CQP Query Language ...
    ... would be: [word="ptic(a|ama|e|i|o|om|u)"] [word="pevačic(a|ama|e|i|om|u)"]. In the example slobodan kao ptica (“free as a bird”) the first and the last component inflect as parts of MWU, so the final query would be [word="slobod(an|na|ne|ni|nih|nim|no|nog|noj|nom|nome|nu)"]15 [word="kao"] [word="ptic( ...
    ... full-form lexicon contains one-word form and a sequence of tag-lemma pairs that could correspond to that word form (Schmid, 1997). TreeTagger full- form lexicon does not allow the possibility of a lexicon entry with two or more tag-lemma pairs corresponding to the same word form and having the same PoS ...

  • An Integrated Environment for Management and Exploitation of Linguistic Resources

    Ranka Stanković, Ivan Obradović (2009)
    ... bilingual query Fig. 7 depicts a HTML document in WS4QE with seg- ments containing word forms from the query for the key- word “poreska obaveza” and its English counterpart “tax li- ability”. Identified word forms are marked by underlining Fig. 5 Combining semantic and morphological query ...
    ... place between sounds at mor- pheme boundaries, producing sound changes with frequent exceptions. Thus, for example, the word “otac” (father) has the following 13 word forms: otac, otaca, oče, očevima, očeve, očeva, očevi, ocima, oci, ocem, oce, ocu, oca. B. Serbian wordnet The Serbian ...
    ... related to query formulation. If that morphological ex- pansion is selected, WS4QE finds all inflectional forms for a given word, regardless of whether it is a simple word or a compound, using SMD, and connects these forms by logical “or” relations. In the same way the user chooses whether ...

  • Towards the semantic annotation of SR-ELEXIS corpus: Insights into Multiword Expressions and Named Entities

    Cvetana Krstev, Ranka Stanković, Aleksandra Marković, Teodora Mihajlov (2024)
    Овај рад представља активности на развоју корпуса ELEXIS-sr, српском додатку вишејезичном анотираном корпусу ELEXIS-а, који се састоји од семантичких анотација и репозиторија значења речи. ELEXIS је паралелни вишејезични анотирани корпус на десет европских језика, који може да се користи као вишејезички репер за евалуацију европских језика са мање и средње развијеним ресурсима. Фокус овог рада је на вишечланим изразима и именованим ентитетима, њиховом препознавању у скупу реченица ELEXIS-sr и поређењу са анотацијама на другим језицима. Разматрају се први кораци ...
    полилексемске језинице, именовани ентитет, вишезначност значења речи, складиште смисла, LLOD

  • An Italian-Serbian Sentence Aligned Parallel Literary Corpus

    Saša Moderc, Ranka Stanković, Aleksandra Tomašević, Mihailo Škorić (2023)
    This article presents the construction and relevance of an Italian-Serbian sentence-aligned parallel corpus, delving into the aligned sentences in order to facilitate effective translation between the two languages. The parallel corpus serves as a valuable resource for language experts, researchers, and language enthusiasts, fostering a deeper understanding of linguistic nuances and cultural expressions. By bridging the gap between Serbian and Italian, this corpus opens new avenues for cross-cultural communication and collaboration, and ultimately contributes to the improvement of language-related ...
    Aligned corpus, parallel corpus, Serbian, Italian, literature

  • 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
    ... ical variants, e.g. Ekavian od Ijekavian word form (pogaziti reč/riječ ‘trample the word’, or synonyms (lomiti/polomiti/slomiti vrat ‘break a neck’), complements, adjuncts etc. These tables are complemented with finite-state automata (FSA) that deal with word order, model complements, etc. and that ...
    ... of abusive content similar to (Rezvan et al., 2018) who firstly created an offensive word lexicon and then collected Twitter messages that contain at least one word from the lexicon. As authors noted, presence of a word in a tweet is just an indication of its offensiveness, thus subsequent manual annotation ...
    ... Измењено: 2023-10-14 04:09:01 Multi-word Expressions for Abusive Speech Detection in Serbian Ranka Stanković, Jelena Mitrović, Danka Jokić, Cvetana Krstev Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] Multi-word Expressions for Abusive Speech Detection ...

  • LRMI markup of OER content within the BAEKTEL project

    Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić (2015)
    ... targetUrl, timeRequired, typicalAgeRange, useRightsUrl. The educational role describes the target audience of the content, while educational alignment points out to an established educational framework (or other educational scheme). The educational use is the educational purpose of the resource ...

  • 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.
    semantički veb,otvoreni povezani podaci, vikpodaci,Infoteka, metapodaci časopisa
    ... in the digital age. References Andonovski, Jelena, Branislava Šandrih, and Olivera Kitanović. 2019. “Bilin- gual lexical extraction based on word alignment for improving corpus search.” The Electronic Library. Krstev, Cvetana, Jelena Jaćimović, Branislava Šandrih, and Ranka Stanković. 2019. “Analysis ...

  • Primena ubrzane konsolidacije kod izgradnje nasipa na deonici priključka Novi Beograd – Surčin autoputa ,,Miloš Veliki"

    Aleksa Tomičić (2024)
    Problem koji se javlja prilikom izgradnje objekata na ne konsolidovanom stišljivom tlu jeste pre svega vezan za prevelika sleganja tla usled opterećenja od objekata, najčešće su to objekti putne infrastrukture (nasipi), ili stambeno poslovni objekti. U tu svrhu se,primenjuju različiti vidovi ubrzanja konsolidacije tla. Stoga za potrebe izrade završnog rada Master akademskih studija studijskog programa geotehnika, na Rudarsko-geološkom fakultetu, izvršena je analiza dva najčešće korišćena postupka ubrzanja konsolidacije: predopterećenjem i ugradnjom peščanih drenova. Glavni cilj ovih postupaka je ...
    stišljivo tlo, konsolidacija, ubrzanje konsolidacije, predopterećenje, peščani drenovi

  • A Mathematical Learning Environment Based on Serbian Language Resources

    Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan (2018)
    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 ...
    mathematical content, text processing, mathematical formulae
    ... corpora (up to 2 billion words) with multiple layers of word-level annotation. CQP is a powerful and efficient concordance system which can process query patterns specified both at the character level (specifying a form of an individual word or an annotation) and at the token level (specifying ...
    ... patterns and get statistical information about corpus. Within preparation of the MLES corpus to each word within the corpus the following information is assigned, in the following order:  Word type (noun, verb, adjective, etc.) - POS tagging  Lemma (nominative singular for a noun, infinitive ...
    ... FLOW CONTROL The architecture of the MLES system is based on three main components. The first component is dedicated to corpus processing and alignment with existing lexical resources. (Figure 1). Figure 1. Structure of corpus processing The obtained results are processed text, augmented ...

  • Mine surveying works for the purpose of excavating the remaining reserves of bauxite in the deposit of “Podbracan”

    Aleksandar Milutinović, Aleksandar Ganić, Thamer Rayes Diyab, Rade Tokalić, Meri Ganić (2015)
    ... that the total station be previously tested and recti�ed), and that while carrying out of those operations, one must not strictly look at the alignment of instrument and signal, due to the fact that the lengths of sides are short, but one must also look at the quality of measurement of the instru- ...

  • Дефинисање геотехничких параметара еолских седимената земуснког платоа на основу лабораторијских и теренских SPT испитивања

    Ђорђе Крзман (2024)
    Циљ овог рада је био да се одреде геотехничке караткеристике предметног терена што представља полазну основу за рационално пројектовање и градњу. Истражним бушењем утврђено је да предметни терен изграђују четри лесна хоризонта и три слоја погребене земље до дубине од 22-23 m. Лабораторијским испитивањем добијени су ефективни параметри смичуће чврстоће, где се кохезија најчешће креће између c’=14 и 18 kPa, а угао унутрашњег трења f'= 25 - 30 °. Теренска SPT испитивањем уз коришћење прихваћених корелација у геотехничкој пракси ...
    лес, лабораторија, SPT, корелације, параметри
    ... |moderately to strongly compressible, moderately compacted, brittle, low permeabiliy, with the appearance (96,931 (96,97) Exploratory borehole for alignment |of carbonale concretions and Fe hydroxide, dark yellow to brown in color. Marsh clays appear in the- t a y periormec interlayers, more compressible ...
    ... transgressive Geological border P p g VicrpaxHa 6yuioTuHa 3a Tpacy ca KkOTOM TepeHa - HOBOM3BeneHa (9&,92) (98,92) Exploratory borehole for alignment with ground surface elevation - recently performed VicrpaxHa GyuioTMHa 3a MeTpo cTaHMLy BW2s-2} ca KOTOM TepeHa - HOBOM3Be/leHa a (98,2&) (98 ...
    ... Teonouika rpannua. - . MI NN | onpaona Gyuyomina aa Tpacy oBW2f-1 | BWh-„ | ca koroM Yepena - HooWBenea (96,92) O }, Exploratory borehole for alignment d with ground surface elevation - recentiy performed | onrpaaona Gyuyomaia aa Merpo crauy– oBW2s-2 | BWDMs-2 | a Korow Tepeta - HoBow3BoneNar ...

  • Indexing of textual databases based on lexical resources: A case study for Serbian

    Ranka Stanković, Cvetana Krstev, Ivan Obradović, Olivera Kitanović (2015)
    In this paper we describe an approach to improvement of information retrieval results for large textual databases by pre-indexing documents using bag-of-words and Named Entity Recognition. The approach was applied on a database of geological projects financed by the Republic of Serbia in the last half century. Each document within this database is described by metadata, consisting of several fields such as title, domain, keywords, abstract, geographical location and the like. A bag of words was produced from these ...
    ... the query is analyzed, tokenization is performed (separating into words, where a MWU within quotation marks is treated as one word); 2. for each document and for each word in the query the weight td idf is found; 3. the similarity between the query and the document is ranked based on the sum of weights ...
    ... especially visible when short words that could be parts of other words are used in a search. As explained before, the old system does not require alignment with whole words precisely in order to recognize at least some inflectional forms. This problem is generated by query keywords such as the chemical ...
    ... Search of textual databases (which is in use for several years) is derived from the basic model, which is based on the input of keywords, single or multi-word units (MWU), that can be combined into Boolean expressions. In addition to general search which goes through all fields in the relevant tables, the ...

  • Extensive vibrations of the belt conveyer drive electromotor of a bucket wheel excavator as a result of intesified wear-and-tear of its mount support

    Vesna Damnjanović, Predrag Jovančić, Snežana Aleksandrović (2017)

  • Mesozoic carbonate rocks in Serbia used as dimension stone

    Vesna Matović, Tijana Vojnović Ćalić (2016)
    The building industry in Serbia uses, to a great extent, imported natural stone for architectural purposes. The significance of local deposits, particularly limestones, is not adequately perceived despite the country’s abundance of these valuable resources. Therefore, this study focuses on Serbia’s Mesozoic carbonate rocks, specifically on the deposits of four selected quarries: Klisura, Skrzut, Struganik, and Tisnica. The quality and prospects of the application of these limestones has not yet been the subject of a detailed, comprehensive investigation. Therefore, ...
    Ukrasni kamen, Mezozoik, Krečnjak, Srbija, Petrografija, Fizičko-mehanička svojstva
    ... indicators of their usability. For the appropriate use of natural stone products, it is advisable to consult suitable technical requirements. The alignment of Serbian national standards with the standards of the European Union is in progress. The requirements concerning natural stone slabs for cladding ...