Sehen und Verstehen: Der Beitrag bildlicher Information zur robusten Sprachverarbeitung

  title={Sehen und Verstehen: Der Beitrag bildlicher Information zur robusten Sprachverarbeitung},
  author={Wolfgang Menzel},
  booktitle={GI Jahrestagung},
  • W. Menzel
  • Published in GI Jahrestagung 1998
  • Computer Science
Sprachverstehen ist in hohem Mase situativ beeinflust. Um diese Charakteristik des menschlichen Vorbilds in technische Losungen zu ubertragen, wird eine Verarbeitungsarchitektur entwickelt, die in der Lage ist, sehr unterschiedliche informationelle Beitrage in einem einheitlichen Entscheidungsverfahren zusammenzufassen. Am Beispiel eines Einsatzes in Lehrsystemen fur den Premdsprachenunterricht wird gezeigt, wie propositional reprasentierte piktorielle Information eine robuste Analyse von… 
Parsing mit inkonsistenten Grammatiken
  • W. Menzel
  • Philosophy, Computer Science
  • 2002
A novel approach to the parsing of natural language based on weighted constraints is presented, focussing on robustness against deviating utterances and external temporal pressure.


Constraint-based Diagnosis for Intelligent Language Tutoring Systems
A solution is presented which provides language learning systems with the desired diagnostic capabilities for a wide range of syntactic, semantic, and domain--related phenomena.
Modeling dependency grammar with restricted constraints
Dans cet article, l'analyse syntaxique avec une grammaire de dependance est modelise comme un probleme de satisfaction de contraintes. L'article decrit un type particulier de contraintes, assez
Generation of language models using the results of image analysis
A new approach towards using contextual information to enhance speech recognition and understanding is presented and Dynamically inferred knowledge about the context is used in addition to the static linguistic and domain speci c knowledge.
Natural Language Parsing: Psychological, Computational, and Theoretical Perspectives
Introduction Laurie Karttunen and Arnold M. Zwicky 1. Measuring syntactic complexity relative to discourse context Alice Davison and Richard Lutz 2. Interpreting questions Elisabet Engdahl 3. How can
An Efficient Distribution of Labor in a Two Stage Robust Interpretation Process
This paper presents an alternative approach where the labor is distributed between a more restrictive partial parser and a repair module, making it possible to achieve a similar run time advantage over MDP without losing the quality of domain independence.
Decision Procedures for Dependency Parsing Using Graded Constraints
We present an approach to the parsing of dependency structures which brings together the notion of parsing as candidate elimination, the use of graded constraints, and the parallel disambiguation of
From a Logical Point of View
It is the wish of the author to keep general terms distinct from abstract singular terms, so that the over-all dis­ pensability of some assumption that has always rankled as ad hoc and unintuitive is discovered.
Eliminative Parsing with Graded Constraints
Graded constraints are used as means to express well-formedness conditions of different strength and to decide which partial structures are locally least preferred and, hence, can be deleted.
From Cognitive Semantics to Lexical Pragmatics: The Functional Polysemy of Discourse Particles
This methodologically interdisciplinary study not only presents a general model of polysemy which includes structural aspects, a conceptual background frame, and the contribution of the lexeme, it also provides full coverage for the functional readings of discourse particles and a unified definition of the word class.
Robust Processing of Natural Language
The paper analyses the necessary preconditions for achieving a higher degree of robustness in natural language processing and suggests a quite different approach based on a procedure for structural disambiguation that not only offers the possibility to cope with robustness issues in a more natural way but eventually might be suited to accommodate quite different aspects of robust behaviour within a single framework.