Real-Time Natural Language Generation in NL-SOAR

  title={Real-Time Natural Language Generation in NL-SOAR},
  author={Robert Rubinoff and Jill Fain Lehman},
NL-Soar is a computer system that performs language comprehension and generation within the framework of the Soar architecture [New90]. NL-Soar provides language capabilities for systems working in a real-time environment. Responding in real time to changing situations requires a flexible way to shift control between language and task operations. To provide this flexibility, NL-Soar organizes generation as a sequence of incremental steps that can be interleaved with task actions as the… 

Figures from this paper

Reactive Natural Language Processing: Comprehension and Generation in the Air Combat Domain
NL-Soar, a language comprehension and generation capability designed to provide integrated, real-time natural language processing for systems built within the Soar architecture, is introduced.
Architectures for Natural Language Generation: Problems and Perspectives
Guided by the identification of major generation challenges viewed from the angles of knowledge-based systems and cognitive psychology, some new directions for future research are sketched.
Chart Generation Using Production Systems
The purpose of this paper is to extend the range of implementation options available to the NLG practitioner by detailing the specific advantages and disadvantages of using production systems for NLG.
Cognitive Modeling Approaches to Language Comprehension Using Construction Grammar
The relationship between modeling human sentence comprehension using cognitive architectures and approaches to linguistic knowledge representation using construction grammars is examined and the tradeoffs between alternative approaches to representing and accessing linguistic knowledge within a cognitive architecture are examined.
Behavior-based Language Generation for Believable Agents
Hap, the behavior-based architecture for believable non-linguistic agents, is extended to better support natural language text generation, and these extensions allow the agent to tightly integrate generation with other aspects of the agent, including action, perception, inference and emotion.
A Gentle Introduction to Soar, an Architecture for Human Cognition.
Abstract : Many intellectual disciplines contribute to the field of cognitive science: psychology, linguistics, anthropology, and artificial intelligence, to name just a few. Cognitive science itself
Comparing Agent Modeling For Language and Action
It is shown how for discourse processing, it is possible to have the benefits of viewing agents in terms of their beliefs and intentions without sacrificing real-time performance and reactivity.
Personality-rich believable agents that use language
Hap, the behavior-based architecture used by the Oz group to construct non-linguistic believable agents, is extended to support natural language text generation, to tightly integrate text generation with other aspects of the agent, including action, perception, inference and emotion.
Wishful: A Discourse Planning System That Considers a User's Inferences
A discourse planner is described that takes into consideration a user's inferences during content planning and discourse organization and also to determine the suitability of the discourse produced by WISHFUL for different types of users.
Robots That Use Language
This article surveys the use of natural language in robotics from a robotics point of view, where robots must map words to aspects of the physical world mediated by the robot's brain.


Integrating knowledge sources in language comprehension
NLSoar is presented, a language comprehension system that integrates disparate knowledge sources automatically and applies all the relevant knowledge sources simultaneously to each word.
The soar papers : research on integrated intelligence
The Soar Papers provide in one place the important ideas that have emerged from the Soar Project, an investigation into the architecture underlying intelligent behaviour with the goal of developing and applying a unified theory of natural and artificial intelligence.
Unified Theories of Cognition
Introduction The Nature of Theories What Are Unified Theories of Cognition? Is Psychology Ready for Unified Theories? The Task of the Book Foundations of Cognitive Science Behaving Systems Knowledge
Intelligent Automated Agents for Tactical Air Simulation: A Progress Report
This article reports on recent progress one (1-v-1) Beyond Visual Range (BVR) in the development of TacAir-Soar, an tactical air scenarios, and the non-jinking intelligent automated agent for tactical air bogey scenarios.
Experiences in interruptible language processing
  • Proceedings of the 1994 AAAI Spring Symposium on Active NLP
  • 1994
ModSAF behavior simulation and control In 3rd Conference on Computer Generated Forces and Behavioral Representation
  • ModSAF behavior simulation and control In 3rd Conference on Computer Generated Forces and Behavioral Representation
  • 1993
Lectures on Government and Binding. Foils Publications
  • Lectures on Government and Binding. Foils Publications
  • 1981