Please use this identifier to cite or link to this item: doi:10.22028/D291-24909
Title: X2MORF : a morphological component based on augmented two-level morphology
Author(s): Trost, Harald
Language: English
Year of Publication: 1991
OPUS Source: Kaiserslautern ; Saarbrücken : DFKI, 1991
SWD key words: Künstliche Intelligenz
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: In this paper I describe X2MORF, a language-independent morphological component for the recognition and generation of word forms based on a lexicon of morphs. The approach is an extension of two-level morphology. The extensions are motivated by linguistic examples which call into question an underlying assumption of standard two-level morphology, namely the independence of morphophonology and morphology as exemplified by two-level rules and continuation classes. Accordingly, I propose a model which allows for interaction between the two parts. Instead of using continuation classes, word formation is described in a feature-based unification grammar. Two-level rules are provided with a morphological context in the form of feature structures. Information contained in the lexicon and the word formation grammar guides the application of two-level rules by matching the morphological context against the morphs. I present an efficient implementation of this model where rules are compiled into automata (as in the standard model) and where processing of the feature-based grammar is enhanced using an automaton derived from that grammar as a filter.
Link to this record: urn:nbn:de:bsz:291-scidok-36706
Series name: Research report / Deutsches Forschungszentrum für Künstliche Intelligenz [ISSN 0946-008x]
Series volume: 91-04
Date of registration: 28-Jun-2011
Faculty: SE - Sonstige Einrichtungen
Department: SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
RR_91_04.pdf132,57 kBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.