Survey of the state of the art in natural language generation: Core tasks, applications and evaluation
This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …
A Review of Natural-Language-Instructed Robot Execution Systems
It is natural and efficient to use human natural language (NL) directly to instruct robot task
executions without prior user knowledge of instruction patterns. Currently, NL-instructed …
executions without prior user knowledge of instruction patterns. Currently, NL-instructed …
Merge-and-shrink abstraction: A method for generating lower bounds in factored state spaces
Many areas of computer science require answering questions about reachability in
compactly described discrete transition systems. Answering such questions effectively …
compactly described discrete transition systems. Answering such questions effectively …
[LIVRE][B] Reinforcement learning for adaptive dialogue systems: a data-driven methodology for dialogue management and natural language generation
The past decade has seen a revolution in the field of spoken dialogue systems. As in other
areas of Computer Science and Artificial Intelligence, data-driven methods are now being …
areas of Computer Science and Artificial Intelligence, data-driven methods are now being …
Lifted successor generation using query optimization techniques
The standard PDDL language for classical planning uses several first-order features, such
as schematic actions. Yet, most classical planners ground this first-order representation into …
as schematic actions. Yet, most classical planners ground this first-order representation into …
Polynomial-time in PDDL input size: Making the delete relaxation feasible for lifted planning
Polynomial-time heuristic functions for planning are commonplace since 20 years. But
polynomial-time in which input? Almost all existing approaches are based on a grounded …
polynomial-time in which input? Almost all existing approaches are based on a grounded …
Planning for social interaction in a robot bartender domain
A robot coexisting with humans must not only be able to perform physical tasks, but must
also be able to interact with humans in a socially appropriate manner. In many social …
also be able to interact with humans in a socially appropriate manner. In many social …
Automatically classifying user engagement for dynamic multi-party human–robot interaction
A robot agent designed to engage in real-world human–robot joint action must be able to
understand the social states of the human users it interacts with in order to behave …
understand the social states of the human users it interacts with in order to behave …
Natural language generation as planning under uncertainty for spoken dialogue systems
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken
Dialogue Systems, based on statistical planning, given noisy feedback from the current …
Dialogue Systems, based on statistical planning, given noisy feedback from the current …
[PDF][PDF] TattleTale: storytelling with planning and large language models
We explore how automated planning can be applied to Natural Language text generation in
order to create narratives (stories) that are coherent and believable. While Large Language …
order to create narratives (stories) that are coherent and believable. While Large Language …