prikaz prve stranice dokumenta An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model
  Download
PDF 8.07 MB
doctoral thesis
An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model
Varaždin: University of Zagreb, Faculty of Organization and Informatics, 2019. urn:nbn:hr:211:639527
Orešković, Marko
University of Zagreb
Faculty of Organization and Informatics

Institutional repository: Faculty of Organization and Informatics - Digital Repository

Cite this document

Orešković, M. (2019). An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model (Doctoral thesis). Varaždin: University of Zagreb, Faculty of Organization and Informatics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:211:639527

Orešković, Marko. "An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model." Doctoral thesis, University of Zagreb, Faculty of Organization and Informatics, 2019. https://urn.nsk.hr/urn:nbn:hr:211:639527

Orešković, Marko. "An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model." Doctoral thesis, University of Zagreb, Faculty of Organization and Informatics, 2019. https://urn.nsk.hr/urn:nbn:hr:211:639527

Orešković, M. (2019). 'An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model', Doctoral thesis, University of Zagreb, Faculty of Organization and Informatics, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:211:639527

Orešković M. An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model [Doctoral thesis]. Varaždin: University of Zagreb, Faculty of Organization and Informatics; 2019 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:211:639527

M. Orešković, "An Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model", Doctoral thesis, University of Zagreb, Faculty of Organization and Informatics, Varaždin, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:211:639527

Metadata
TitleAn Online Syntactic and Semantic Framework for Lexical Relations Extraction Using Natural Language Deterministic Model
Title (croatian)Mrežni sintaksno-semantički okvir za izvlačenje leksičkih relacija deterministričkim modelom prirodnog jezika
AuthorMarko Orešković
MBZ: 374415
MentorMirko Čubrilo (mentor)
MBZ: 135963
MentorMario Essert (komentor)
MBZ: 73841
Committee memberJasminka Dobša (predsjednik povjerenstva)
MBZ: 218640
Committee memberSanja Seljan (član povjerenstva)
MBZ: 219255
Committee memberMarkus Schatten (član povjerenstva)
MBZ: 291806
GranterUniversity of Zagreb
Faculty of Organization and Informatics
Varaždin
Defense date and country2019-03-15, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Universal decimal classification
(UDC)		004 - Computer science and technology. Computing. Data processing
Abstract
Given the extraordinary growth in online documents, methods for automated extraction of semantic relations became popular, and shortly after, became necessary. This thesis proposes a new deterministic language model, with the associated artifact, which acts as an online Syntactic and Semantic Framework (SSF) for the extraction of morphosyntactic and semantic relations. The model covers all fundamental linguistic fields: Morphology (formation, composition, and word paradigms), Lexicography (storing words and their features in network lexicons), Syntax (the composition of words in meaningful parts: phrases, sentences, and pragmatics), and Semantics (determining the meaning of phrases). To achieve this, a new tagging system with more complex structures was developed. Instead of the commonly used vectored systems, this new tagging system uses tree-likeT-structures with hierarchical, grammatical Word of Speech (WOS), and Semantic of Word (SOW) tags. For relations extraction, it was necessary to develop a syntactic (sub)model of language, which ultimately is the foundation for performing semantic analysis. This was achieved by introducing a new ‘O-structure’, which represents the union of WOS/SOW features from T-structures of words and enables the creation of syntagmatic patterns. Such patterns are a powerful mechanism for the extraction of conceptual structures (e.g., metonymies, similes, or metaphors), breaking sentences into main and subordinate clauses, or detection of a sentence’s main construction parts (subject, predicate, and object). Since all program modules are developed as general and generative entities, SSF can be used for any of the Indo-European languages, although validation and network lexicons have been developed for the Croatian language only. The SSF has three types of lexicons (morphs/syllables, words, and multi-word expressions), and the main words lexicon is included in the Global Linguistic Linked Open Data (LLOD) Cloud, allowing interoperability with all other world languages. The SSF model and its artifact represent a complete natural language model which can be used to extract the lexical relations from single sentences, paragraphs, and also from large collections of documents.
Abstract (croatian)
Pojavom velikoga broja digitalnih dokumenata u okružju virtualnih mreža (interneta i dr.), postali su zanimljivi, a nedugo zatim i nužni, načini identifikacije i strojnoga izvlačenja semantičkih relacija iz (digitalnih) dokumenata (tekstova). U ovome radu predlaže se novi, deterministički jezični model s pripadnim artefaktom (Syntactic and Semantic Framework - SSF), koji će služiti kao mrežni okvir za izvlačenje morfosintaktičkih i semantičkih relacija iz digitalnog teksta, ali i pružati mnoge druge jezikoslovne funkcije. Model pokriva sva temeljna područja jezikoslovlja: morfologiju (tvorbu, sastav i paradigme riječi) s leksikografijom (spremanjem riječi i njihovih značenja u mrežne leksikone), sintaksu (tj. skladnju riječi u cjeline: sintagme, rečenice i pragmatiku) i semantiku (određivanje značenja sintagmi). Da bi se to ostvarilo, bilo je nužno označiti riječ složenijom strukturom, umjesto do sada korištenih vektoriziranih gramatičkih obilježja predložene su nove T-strukture s hijerarhijskim, gramatičkim (Word of Speech - WOS) i semantičkim (Semantic of Word - SOW) tagovima. Da bi se relacije mogle pronalaziti bilo je potrebno osmisliti sintaktički (pod)model jezika, na kojem će se u konačnici graditi i semantička analiza. To je postignuto uvođenjem nove, tzv. O-strukture, koja predstavlja uniju WOS/SOW obilježja iz T-struktura pojedinih riječi i omogućuje stvaranje sintagmatskih uzoraka. Takvi uzorci predstavljaju snažan mehanizam za izvlačenje konceptualnih struktura (npr. metonimija, simila ili metafora), razbijanje zavisnih rečenica ili prepoznavanje rečeničnih dijelova (subjekta, predikata i objekta). S obzirom da su svi programski moduli mrežnog okvira razvijeni kao opći i generativni entiteti, ne postoji nikakav problem korištenje SSF-a za bilo koji od indoeuropskih jezika, premda su provjera njegovog rada i mrežni leksikoni izvedeni za sada samo za hrvatski jezik. Mrežni okvir ima tri vrste leksikona (morphovi/slogovi, riječi i višeriječnice), a glavni leksikon riječi već je uključen u globalni lingvistički oblak povezanih podataka, što znači da je interoperabilnost s drugim jezicima već postignuta. S ovako osmišljenim i realiziranim načinom, SSF model i njegov realizirani artefakt, predstavljaju potpuni model prirodnoga jezika s kojim se mogu izvlačiti leksičke relacije iz pojedinačne rečenice, odlomka, ali i velikog korpusa (eng. big data) podataka.
Keywords
Keywords (croatian)
Languageenglish
DOIhttps://doi.org/10.13140/RG.2.2.31092.19849
URN:NBNurn:nbn:hr:211:639527
Study programmeTitle: Postgraduate doctoral study in Information Science
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, područje društvenih znanosti, polje informacijske i komunikacijske znanosti (doktor/doktorica znanosti, područje društvenih znanosti, polje informacijske i komunikacijske znanosti)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-04-04 10:21:54