Automated Planning for Situated Natural Language Generation
نویسندگان
چکیده
We present a natural language generation approach which models, exploits, and manipulates the non-linguistic context in situated communication, using techniques from AI planning. We show how to generate instructions which deliberately guide the hearer to a location that is convenient for the generation of simple referring expressions, and how to generate referring expressions with context-dependent adjectives. We implement and evaluate our approach in the framework of the Challenge on Generating Instructions in Virtual Environments, finding that it performs well even under the constraints of realtime generation.
منابع مشابه
Combining Hierarchical Reinforcement Learning and Bayesian Networks for Natural Language Generation in Situated Dialogue
Language generators in situated domains face a number of content selection, utterance planning and surface realisation decisions, which can be strictly interdependent. We therefore propose to optimise these processes in a joint fashion using Hierarchical Reinforcement Learning. To this end, we induce a reward function for content selection and utterance planning from data using the PARADISE fra...
متن کاملArchitectures for Natural Language Generation: Problems and Perspectives
Current research in natural language generation is situated in a computational linguistics tradition that was founded several decades ago. We critically analyse some of the architectural assumptions underlying existing systems and point out some problems in the domains of text planning and lexicalization. Guided by the identification of major generation challenges viewed from the angles of know...
متن کامل“Situated AI” in Video Games: Integrating NLP, Path Planning and 3D Animation
This paper investigates the integration of Artificial Intelligence techniques into video games, from the perspective of voice controlled adventure games. Speech-based interfaces would add new dimensions to the control of video games. However, the integration of speech raises several issues, such as the adequate level of interpretation that should be carried by the system. We describe the implem...
متن کاملTechniques for Text Planning with XSLT
We describe an approach to text planning that uses the XSLT template-processing engine to create logical forms for an external surface realizer. Using a realizer that can process logical forms with embedded alternatives provides a substitute for backtracking in the text-planning process. This allows the text planner to combine the strengths of the AI-planning and template-based traditions in na...
متن کاملPlanning in AI and Text Planning in Natural Language Generation
Researchers in natural language generation are becoming increasingly aware of the similarities between the task of planning the content and structure of the natural language text and that of other AI planning tasks. The problem of text planning and other AI planning problems have been studied separately from each other, and while many overlapping results have been found, they have not been shar...
متن کامل