Controlling a Language Generation Planner
نویسندگان
چکیده
The set of partially interdependent lexical and syntactic decisions that have to be made in the process of natural language generation are best seen as a complex planning and search problem. This paper discusses the phenomena involved in natural language generation planning and argues that a blackboard-type architecture with agenda-style control is more appropriate for this task than a sequential control architecture with backtracking. The blackboard architecture we describe is implemented in the language generator DIOGENES.
منابع مشابه
Model-level Automatic Test Generation for Uml Statecharts
We present a framework for model-level testing of behavioral UML models. For automatic test generation, we use planner algorithms to deal with the complexity of UML models. Our approach is characterized by an automatic and metamodeldriven transformation from UML statecharts to a tool independent representation of planner algorithms from which the input language of concrete planner tools can be ...
متن کاملUsing a Textual Representational Level Component in the Context of Discourse or Dialogue Generation
A natural language generation system is typically constituted by two main components: a content planning component (e.g., text planner or dialogue act planner) and a linguistic realization component. But, this is not suucient since, on the one hand, the message built by the content planning component is generally not adequately detailed in order to control the many possibilities for its express...
متن کاملEvaluating a Trainable Sentence Planner for a Spoken Dialogue System
Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rulebased approaches. In this paper We experimentally evaluate a trainable sentence planner for a spoken dialogue system by eliciting subjective...
متن کاملStochastic Template-based Surface Realization — RPE Report
Introduction Natural language processing (NLP) is the branch of information science that deals with natural language information [2]. It can refer to anything from simple string-manipulation tasks to higher-level AI-like tasks like prcessing user queries [1]. The two areas of NLP that deal with syntax are natural language understanding (NLU) and natural language generation (NLG). NLU involves m...
متن کاملDescription-directed Natural Language Generation
We report here on a significant new set of capabilities that we have incorporated into our language generation system MUMBLE. Their impact will be to greatly simplify the work of any text planner that uses MUMBLE as ita linguistics component since MUMBLE can now take on many of the planner's text organization and decision-making problems with markedly less hand-tailoring of algorithms in either...
متن کامل