Survey of the state of the art in natural language generation: Core tasks, applications and evaluation

A Gatt, E Krahmer - Journal of Artificial Intelligence Research, 2018 - jair.org
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 …

A Review of Natural-Language-Instructed Robot Execution Systems

R Liu, Y Guo, R **, X Zhang - AI, 2024 - mdpi.com
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 …

Merge-and-shrink abstraction: A method for generating lower bounds in factored state spaces

M Helmert, P Haslum, J Hoffmann… - Journal of the ACM (JACM), 2014 - dl.acm.org
Many areas of computer science require answering questions about reachability in
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

V Rieser, O Lemon - 2011 - books.google.com
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 …

Lifted successor generation using query optimization techniques

AB Corrêa, F Pommerening, M Helmert… - Proceedings of the …, 2020 - ojs.aaai.org
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 …

Polynomial-time in PDDL input size: Making the delete relaxation feasible for lifted planning

P Lauer, A Torralba, D Fišer, D Höller… - … 2021 Workshop on …, 2021 - openreview.net
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 …

Planning for social interaction in a robot bartender domain

R Petrick, ME Foster - Proceedings of the International Conference on …, 2013 - ojs.aaai.org
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 …

Automatically classifying user engagement for dynamic multi-party human–robot interaction

ME Foster, A Gaschler, M Giuliani - International Journal of Social …, 2017 - Springer
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 …

Natural language generation as planning under uncertainty for spoken dialogue systems

V Rieser, O Lemon - Conference of the European Association for …, 2009 - Springer
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 …

[PDF][PDF] TattleTale: storytelling with planning and large language models

N Simon, C Muise - ICAPS Workshop on Scheduling …, 2022 - icaps22.icaps-conference.org
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 …