Εργαστήριο Επεξεργασίας Φυσικής Γλώσσας
Natural Language Processing Laboratory

ανακοινώσεις - announcements

μαθήματα - courses

έρευνα - research

δημοσιεύσεις - publications

συνέδρια - conferences

ενδιαφέροντες σύνδεσμοι - interesting links

Μέλη Ερευνητικής Ομάδας - επικοινωνία

Research Group Members -Contacts

research

  • Research interests
  • Developmental Systems - Standards
  • Bibliographic Data Bases
  • Funded Research Programs
  •  

    Research Interests
    • Standardization (Greek Character Sets, Keyboards, Transliteration / Transcription, Cultural Elements)
    • Literary and Linguistic Computing (Text Normalization, Tagging, Sorting, Lexica Generation, Concordance Lists, Lexical Data Bases)
    • Computational Grammars (Morphological and Syntactic Analysis, Semantic features and Linguistic Knowledge Representation)
    • Natural Language Front Ends (Databases and Intelligent Agents' Interfacing)
    • Computing Terminology
    • Information Technology impacts on Society -- especially on Education.
     
    Developmental Systems - Standards

    Contribution to the Standardization and development of the standards:

    • Greek Character Sets� Repertoire: ΕΛΟΤ 927, ISO 8859/7 (ΕΛΟΤ 928), ISO 10646 (Greek Planes)
    • Greek - Latin Keyboard: ΕΛΟΤ 1000
    • Greek script and texts� Transliteration and Transcription: ISO 843 (ΕΛΟΤ 743)

     

    Software tools in the field: Literary and Linguistic Computing: Text Normalization and Tagging, Sorting, semi-automatic Lexica Generation, Concordance Lists, Lexical Data Bases (1985)

    "Synthetis" (Συνθέτης), the first Text Editor for Modern Greek developed for the MS-DOS platform (Greek Productivity Center, 1986).

    Morphological analyzers - annotating software tools for Modern Greek:

    • "Lexifanis" (Λεξιφάνης), the first Morphological Analyzer - Part of Speech Tagger for Modern Greek, based on finite state automata (1985)
    • "QuickLem" (Ωκυλήμμα) decision table driven Part of Speech Tagger (1987)

    Linguistic Knowledge Base System "Keimenopoietis" (Κειμενοποιητής) to represent Morphological, Syntactic and Semantic features of the Greek language, implementing PATR II - Unification Grammar formalism (NTUA, 1991).

    Lemmatiser "QuickLem" for Modern Greek. QuickLem functions for nouns and adjectives presently; the Verb system is under development (NTUA, 2000)

    Bibliographic Data Bases

    Greek Linguistic Bibliography Database.

    Greek Science Bibliography A (polytonic Greek) Database developed for a NTUA Library project, Prof. M. Asimakopoulos NTUA (NTUA, 2000).

     
    Funded Research Programs

    EUROTRA Members of the NLP Lab offered support as computer experts to the Greek Team. Greek Text Normalisation tools (sentence splitter, delimiters' tagger), concordance lists. Lexical Databases. (European Community, 1985 - 1988)

    Controlled Language Checker "Schematopoiesis". A technical document checker for Controlled Modern Greek in collaboration with ILSP, Demokritos, Unisoft and ALTEC. (Greek General Secretariat of R&D, 1999-2001), URL: http://schema.glotta.ntua.gr

    Basic Research for the verb. Translational Equivalence Database for the Greek - English verbal pairs. Representation of syntactic and semantic characteristics for Greek and English verbs. (NTUA, 2000-2002)

    ML-Images! European "e-Content" program (2001-2003).
    Technical Report: A Web based Multilingual Indexing and Retrieval System

    Basic Research for Greek words' semantics. Ontology design for the Vostantzoglou 'Antilexicon', a concept-based Lexicon for Modern Greek. (NTUA, 2004-2006).

     
    Bibliography - State of the Art (collection)