Manfred Gehrke

Resolving Anaphoric References in a DRT-based Dialogue System

The identification of the referents of pronouns and definite descriptions in natural language processing (NLP) is a formidable task. We present our approach to pronominal and definite references in a German language dialogue system that is currently being implemented. This approach combines immediate focus and a special purpose reasoner that uses a KL-ONE like taxonomy within a modified form of discourse representation theory (DRT) structure (KAMP 81, HUNZE 88).

A user friendly ATN Programming Environment (APE)

APE is a workbench to develop ATN grammars based on an active chart parser. It represents the networks graphically and supports the grammar writer by window-and menu-based debugging techniques.

Begriffsdefinitionen und Referenzidentifikation definiter Beschreibungen: Neues aus der Beziehungskiste

Bei der Referenzidentifikation definiter Beschreibungen spielen bestimmte Relationen zwischen Begriffen eine wichtige Rolle. In dieser Arbeit wird beschrieben, auf welche Art und Weise lexikalisch-semantische Relationen in einer’term definition language’ (TDL, vgl. [BRACHMAN85]), wie QUIRK [BERGMANN87], reprasentiert werden konnen, und welche Auswirkung dies auf die Definition von Begriffen hat.

Modelling Heuristic Parsing Strategies

Besides a correct grammar, the strategy that applies the grammar rules to the input plays an important role in the performance of natural language parsers. In this paper a framework is presented offering comprehenensive facilities for defining and testing parsing strategies based on various heuristic criteria.

Adapting a Large Scale MT System for Spoken Language

This paper describes an attempt to transform a general purpose machine translation system that had originally been designed for human aided computer translation of technical documentation into the linguistic component of a domain dependent spoken language translation system for remote PC maintenance. In the first part, the translation system is described. The second part describes the measures taken to adapt it to the spoken language task.

German-Japanese Speech Translation in CSTAR

The CSTAR project focusses on research to show the feasibility of speech-to-speech translation in telephone services. This paper describes the architecture and the main components of this system which translates spoken German utterances into spoken Japanese utterances.

GNEIS: a Portable Natural Language Explanation Component for Expert Systems

GNEIS is the adaption of the Linguistic Kernel Processor (LKP), a general purpose natural langage processing system, to the expert system toolbox Domino Expert as an explanation module. The explanation of the decision made by the expert system is achieved by mapping the expert system predicates via several steps into a semantic form, the input to the generation component of the LKP. Adaption tools to construct the conversion rules and to build up the lexicon provide for the portability of this system.

Sprachanalyse und Textgenerierung im natürlich-sprachlichen Beratungssystem WISBER

Im BMFT-Verbundprojekt WISBER wurde der Prototyp eines naturlichsprachlichen Beratungssystems entwickelt. Als exemplarischer Diskursbereich wurde die Geldanlage gewahlt. Neben den Komponenten, die das Beratungswissen der Domane und den Beratungsvorgang modellieren (vgl. hierzu im Detail [Bergmann/Gerlach 87]), stellen die Komponenten zur Sprachanalyse und zur Textgenerierung wesentliche Module des Systems dar, da sie die unmittelbare Kommunikation mit dem Benutzer realisieren. Dies geschieht in der Form eines in Deutsch gefuhrten, gemischt-initiativen Dialogs, in dem die fur eine Beratung notwendige Information ermittelt und das Beratungsergebnis naturlichsprachlich mitgeteilt wird.