LINGUIST List 21.3621

Tue Sep 14 2010

Diss: Comp Ling/Morphology/Syntax: Faaß: 'A Morpho-Syntactic ...'

Editor for this issue: Mfon Udoinyang <mfonlinguistlist.org>


        1.    Gertrud Faaß, A Morpho-Syntactic Description of Northern Sotho as a Basis for an Automated Translation from Northern Sotho to English

Message 1: A Morpho-Syntactic Description of Northern Sotho as a Basis for an Automated Translation from Northern Sotho to English
Date: 13-Sep-2010
From: Gertrud Faaß <gertrud.faaszims.uni-stuttgart.de>
Subject: A Morpho-Syntactic Description of Northern Sotho as a Basis for an Automated Translation from Northern Sotho to English
E-mail this message to a friend

Institution: University of Pretoria Program: Department of African Languages Dissertation Status: Completed Degree Date: 2010

Author: Gertrud Faaß

Dissertation Title: A Morpho-Syntactic Description of Northern Sotho as a Basis for an Automated Translation from Northern Sotho to English

Dissertation URL: http://www.ims.uni-stuttgart.de/~faaszgd/PhD-thesis.html

Linguistic Field(s): Computational Linguistics                             Morphology                             Syntax
Subject Language(s): Sotho, Northern (nso)
Dissertation Director:
Ulrich Heid Danie Jacobus Prinsloo
Dissertation Abstract:

This PhD thesis provides a morpho-syntactic description of Northern Sothofrom a computational perspective. While a number of publications describemorphological and syntactical aspects of this language, mostly in the formof prescriptive study books (e.g. Lombard (1985); Van Wyk et al. (1992);Poulos and Louwrens (1994)) or of descriptive articles (e.g. Anderson andKotzé (2006); Kosch (2006); De Schryver and Taljard (2006)), so far nocomprehensive description is available that would provide a basis fordeveloping a rule-based parser to analyse Northern Sotho on sentence level.This study attempts to fill the gap.

Northern Sotho morpho-syntactic phenomena are explored which results in thefollowing descriptions: Language units (tokens) of Northern Sotho areidentified. These are sorted into word class categories (parts of speech),using the descriptions of Taljard et al. (2008) as a basis; the formalrelationships between these units are described in the form of productivemorpho-syntactic phrase grammar rules. These rules are defined within theframework of generative grammar. Additionally, an attempt is made to findgeneralisations on the contextual distribution of the many items containedin verbs that are polysemous in terms of their parts of speech.

The grammar rules described in the preceding chapter are now explored inorder to find patterns in the co-occurrence of parts of speech leadingtowards a future, more general linguistic modelling of Northern Sothoverbs. It is also shown how a parser could work its way step-by-step doingan analysis of a complete sentence making use of a lexicon and the rulesdeveloped here. A number of relevant phrase grammar rules have also beenimplemented as a constraint-based grammar fragment, in line with the theoryof Lexical-Functional Grammar (LFG, Kaplan and Bresnan, 1982). Here, weutilized the Xerox Linguistic Environment (XLE) (with permission from theXerox Palo Alto Research Centre (PARC).

Lastly, the study contains some basic definitions for a proposed machinetranslation (MT) into English attempting to support the development ofMT-rules. An introduction to MT and a first contrastive description ofphenomena of both languages is provided.



Page Updated: 14-Sep-2010