22.3167, Diss: Comp Ling: Mahlow: 'Linguistisch Unterst=?iso-8859-1?Q?=FCtztes_?=Redigieren: ...'

[linguist at LINGUISTLIST.ORG]

LINGUIST List: Vol-22-3167. Mon Aug 08 2011. ISSN: 1068 - 4875.

Subject: 22.3167, Diss: Comp Ling: Mahlow: 'Linguistisch Unterstütztes Redigieren: ...'

Moderators: Anthony Aristar, Eastern Michigan U <aristar at linguistlist.org>
            Helen Aristar-Dry, Eastern Michigan U <hdry at linguistlist.org>
 
Reviews: Veronika Drake, U of Wisconsin-Madison  
Monica Macaulay, U of Wisconsin-Madison  
Rajiv Rao, U of Wisconsin-Madison  
Joseph Salmons, U of Wisconsin-Madison  
Anja Wanner, U of Wisconsin-Madison  
       <reviews at linguistlist.org> 

Homepage: http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, 
and donations from subscribers and publishers.

Editor for this issue: Mfon Udoinyang <mfon at linguistlist.org>
================================================================  

To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.cfm.

===========================Directory==============================  

1)
Date: 05-Aug-2011
From: Cerstin Mahlow [mahlow at cl.uzh.ch]
Subject: Linguistisch Unterstütztes Redigieren: Konzept und exemplarische Umsetzung basierend auf interaktiven computerlinguistischen Ressourcen / Linguistically Supported Editing and Revising: Concept and prototypical implementation based on interactive NLP resources
 

	
-------------------------Message 1 ---------------------------------- 
Date: Mon, 08 Aug 2011 14:52:27
From: Cerstin Mahlow [mahlow at cl.uzh.ch]
Subject: Linguistisch Unterstütztes Redigieren: Konzept und exemplarische Umsetzung basierend auf interaktiven computerlinguistischen Ressourcen / Linguistically Supported Editing and Revising: Concept and prototypical implementation based on interactive NLP resources

E-mail this message to a friend:
http://linguistlist.org/issues/emailmessage/verification.cfm?iss=22-3167.html&submissionid=4528821&topicid=14&msgnumber=1
  


Institution: Universität Zürich 
Program: Computational Linguistics 
Dissertation Status: Completed 
Degree Date: 2011 

Author: Cerstin Mahlow

Dissertation Title: Linguistisch Unterstütztes Redigieren: Konzept und
exemplarische Umsetzung basierend auf interaktiven
computerlinguistischen Ressourcen / Linguistically
Supported Editing and Revising: Concept and prototypical
implementation based on interactive NLP resources 

Dissertation URL:  www.lingured.info

Linguistic Field(s): Computational Linguistics

Subject Language(s): German (deu)


Dissertation Director(s):
Michael Hess
Michael Zock

Dissertation Abstract:

Composing, revising, and editing are highly demanding tasks. Even in
polished and published texts from professional writers we can observe
errors and mistakes. For many errors, we can infer how they came to be:
Word processors offer character-based functions only. These functions do
not take into account elements and structures of the language the author is
using.  Authors are thus forced to translate their high-level goals into
long and complex sequences of low-level character-based functions. Both the
translation process and the execution of such sequences of functions are
error-prone. However, in text editors for programmers we find so-called
language-aware editing functions. These functions operate on the elements
and structures of a programming or mark-up language and help to avoid
errors, as language-aware functions make revising and editing less tedious
and error-prone.

We argue that the concept of language awareness can be transferred to
writing natural language texts using word processors. We propose functions
that take the structures of natural languages into consideration. We
distinguish information functions, movement functions, and operations to
support revising and editing. The design is based on current findings from
writing research. 

Language-aware editing functions rely on the recognition and categorization
of relevant elements and structures with respect to a certain language. We
use methods and resources from computational linguistics for morphological
analysis and generation, and for part-of-speech tagging. When evaluating
respective resources we face a rather disappointing situation: NLP
resources for German are less suitable than assumed and less applicable for
real-world applications than usually claimed in the literature.Our
prototypical implementation of language-aware functions for revising and
editing of German texts serves as a proof of concept. The implementation
illustrates opportunities and limits of current NLP resources for German. 







-----------------------------------------------------------
LINGUIST List: Vol-22-3167	
----------------------------------------------------------