scispace - formally typeset
Open AccessProceedings Article

CARAMEL: A Computational Model of Natural Language Understanding Using a Parallel Implementation.

Gérard Sabah
- pp 563-565
Reads0
Chats0
About
This article is published in European Conference on Artificial Intelligence.The article was published on 1990-01-01 and is currently open access. It has received 20 citations till now. The article focuses on the topics: Natural language understanding.

read more

Citations
More filters
Journal ArticleDOI

A multi-agent decision support system for stock trading

TL;DR: The article introduces an architecture, the MASST system architecture, which supports dynamic information and knowledge exchange among the cooperating agents, and uses a dynamic blackboard as an interagent communication paradigm to facilitate factual data, business rule, and command exchange between cooperating MASST agents.
Book ChapterDOI

TALISMAN: A Multi-Agent System for Natuarl Language Processing

TL;DR: This paper presents a general Natural Language Processing system called TALISMAN, which brings openness to dictionary modification, grammars and strategies of analysis, as well as the necessary mechanisms for the integration of new modules.
Dissertation

MICO : La notion de construction située pour un modèle d'interprétation et de traitement de la référence pour le dialogue finalisé

TL;DR: La question de the resolution of the reference est d'une importance majeure lorsque l'on souhaite s'interesser a la genericite dans les systemes de dialogue dans le cas des agents assistants d'interface.
Journal ArticleDOI

Detection of semantic errors in Arabic texts

TL;DR: This paper combines four contextual methods (using statistics and linguistic information) in order to decide about the semantic validity of a word in a sentence and chooses to implement the approach on a distributed architecture.
Proceedings Article

Supporting flexibility and transmutability: multi-agent processing and role-switching in a pragmatically oriented dialog system

TL;DR: Two attempts to achieve the second goal are discussed which have been realized in two different modules of PRACMA: bidirectional, role-independent dialog planning operators; and Bayesian meta-networks for reasoning about the dialog partner’s beliefs and evaluations.
Related Papers (5)