Filters








811,856 Hits in 3.7 sec

EXPERIENCES WITH PLANNING FOR NATURAL LANGUAGE GENERATION

Alexander Koller, Ronald P. A. Petrick
2011 Computational intelligence  
Natural language generation (NLG) is a major subfield of computational linguistics with a long tradition as an application area of automated planning systems.  ...  As a result, we offer our domains and experiences as challenges for the planning community.  ...  Acknowledgements This work arose in the context of the Planning and Language Interest Group at the University of Edinburgh.  ... 
doi:10.1111/j.1467-8640.2010.00370.x fatcat:doylevjmfncphkx2cjtupt6e3q

Balancing Shared Autonomy with Human-Robot Communication [article]

Rosario Scalise, Yonatan Bisk, Maxwell Forbes, Daqing Yi, Yejin Choi, Siddhartha Srinivasa
2018 arXiv   pre-print
Robotic agents that share autonomy with a human should leverage human domain knowledge and account for their preferences when completing a task.  ...  This extra knowledge can dramatically improve plan efficiency and user-satisfaction, but these gains are lost if communicating with a robot is taxing and unnatural.  ...  RELATED WORK Our work is motivated by the rich breadth of research on using natural language to communicate with robots both within the robotics and natural language communities.  ... 
arXiv:1805.07719v1 fatcat:wd2yarewqzbbfbaf66ojcvj2gq

Storytelling, behavior planning, and language evolution in context

Glen McBride
2014 Frontiers in Psychology  
Natural language evolved in conversations with feedback providing understanding of changes.  ...  Storytelling could evolve without need for language yet be strongly subject to natural selection and could provide a major feedback process in evolving language.  ...  To Michael Corballis for many discussions and comments; to Bill von Hippel for reading, comment, and encouragement; to Paul Bloom for encouragement.  ... 
doi:10.3389/fpsyg.2014.01131 pmid:25360123 pmcid:PMC4197760 fatcat:7ryni2bp2fgrhc7ooe6cv3data

PDDL Planning with Natural Language-Based Scene Understanding for UAV-UGV Cooperation

Jiyoun Moon, Beom-Hee Lee
2019 Applied Sciences  
We then generate a sequence of actions for each robot using a planning domain definition language planner. JENA-TDB is used for knowledge acquisition storage.  ...  We employ neural networks for natural-language-based scene understanding to share environmental information among robots.  ...  Introduction Natural language-based scene understanding is a critical issue for symbolic planning for heterogeneous multi-robot cooperation.  ... 
doi:10.3390/app9183789 fatcat:lsfmciw4rvaxvlpwmznuodrqte

Mixing Framework from Next Generation Science Standards (NGSS) to a Local Project

Azita Seyed Fadaei
2018 Communication, Society and Media  
In each country, being familiar with these frameworks helps to conduct teachers to be self-planners for teaching process.  ...  of planning activities related national problems and goals.  ...  The purpose of this paper is introducing the experiences related to study the main programs in curriculum planning for developers and teachers to know how use the resources and frameworks to plan new activities  ... 
doi:10.22158/csm.v1n2p125 fatcat:u7jsua3iy5bqbok3jdo6p7yqam

Skill Induction and Planning with Latent Language [article]

Pratyusha Sharma, Antonio Torralba, Jacob Andreas
2021 arXiv   pre-print
In trained models, the space of natural language commands indexes a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel  ...  We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making.  ...  Learning yields a hierarchical policy in which natural language serves as an abstract representation of subgoals and plans: an controller sub-policy maps from goals to natural language plan specifications  ... 
arXiv:2110.01517v1 fatcat:sfpsl7ce25bftcn2p5635rqkfe

ESEML

Bruno Cartaxo, Italo Costa, Dhiego Abrantes, Andre Santos, Sergio Soares, Vinicius Garcia
2012 Proceedings of the 2012 workshop on Domain-specific modeling - DSM '12  
By using the language, the researcher is guided to define the elements of an experimental plan and connections, which is automatically generated, resulting a complete document of experimental plan.  ...  More specifically, the current version of our proposal generates the experimental plan from the experiment model defined using the DSL.  ...  At last, we present a case of an automatic generation of the experimental plan, which was the starting point for the present study. See a generated plan at http://bit.ly/RusZYm.  ... 
doi:10.1145/2420918.2420933 fatcat:tq6ghsqe6rbu5fy7yo4rmlhzsa

Coordination of Multiple Autonomous Agents Using Naturally Generated Languages in Task Planning

Li Wang, Qiao Guo
2019 Applied Sciences  
Second, we give the sufficient and necessary conditions of a valid abstraction with proofs and develop an efficient algorithm to construct the languages where several words are generated naturally.  ...  Finally, we conduct several experiments to evaluate the benefits of the languages in a variety of scenarios of a path-planning domain.  ...  The language in this work is naturally generated and only depends on planning domains.  ... 
doi:10.3390/app9173571 fatcat:m5mdlnjrxzdurfwnp54gzeqxhm

Under the Influence: Using Natural Language in Interactive Storytelling [chapter]

Marc Cavazza, Fred Charles, Steven J. Mead
2003 IFIP Advances in Information and Communication Technology  
Interacting in natural language with virtual actors is an important aspect of the development of future Interactive Storytelling systems.  ...  We describe a paradigm for speech interfaces in interactive storytelling based on the notion of influence.  ...  Acknowledgements We are indebted to Eric Jacopin for his advice on the choice of planning fonnalisms.  ... 
doi:10.1007/978-0-387-35660-0_1 fatcat:cwyqfbyuw5f3biuvydzccy4wf4

Language-guided Adaptive Perception with Hierarchical Symbolic Representations for Mobile Manipulators [article]

Ethan Fahnestock, Siddharth Patki, Thomas M. Howard
2019 arXiv   pre-print
Language is an effective medium for bi-directional communication in human-robot teams.  ...  Recent algorithms condition the expression of object detectors in a robot's perception pipeline on language to generate a minimal representation of the environment necessary to efficiently determine the  ...  Introduction Natural language provides a powerful medium for communication with artificial agents.  ... 
arXiv:1909.09880v1 fatcat:p6ak36k56ra4xmpvpdxpgwmlxi

Interpreting instruction sequences in spatial language discourse with pragmatics towards natural human-robot interaction

Juan Fasola, Maja J Mataric
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
We present a methodology for enabling service robots to interpret spatial language instruction sequences expressed through natural language discourse from non-expert users.  ...  Towards application of our human-robot interaction (HRI) methodology on robot platforms in practice with end users, we discuss a generalized procedure for transfer to physical systems and provide solutions  ...  ACKNOWLEDGMENT We are grateful to Yixin Cai and Han Xiao for their help with ROS integration, PR2 software development, and in collecting experiment data. We also thank Carlos A.  ... 
doi:10.1109/icra.2014.6907249 dblp:conf/icra/FasolaM14 fatcat:nipoi5t7vngb5cdrn6eixzfusm

Cognitive Process By Students' Majoring in Natural and Social Science in Writing Analytical Exposition Text

Rinda Sari Putri, Anni Holila Pulungan, Rahmad . Husein
2021 Linguistik Terapan  
The students majoring in Natural Science use the information in the assignment to generate new information then relate it with their experience and they know about the topic to be developed.  ...  Whereas, students majoring in Social Science do not really know about the topic and do not relate it with their experience so that way they could not generate content information and develop the text.  ...  to generate new information then relate it with their experience and they know about the topic to be developed.  ... 
doi:10.24114/lt.v17i3.22453 fatcat:adl7cdfm45hglnbkfjgqnhlkca

Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions [article]

Peter A. Jansen
2020 arXiv   pre-print
Our results suggest that contextualized language models may provide strong visual semantic planning modules for grounded virtual agents.  ...  We empirically demonstrate that it is possible to generate gold multi-step plans from language directives alone without any visual input in 26% of unseen cases.  ...  6,574 gold command sequences representing visual semantic plans, each paired with 3 natural language directives describing the goal of those command sequences (e.g.  ... 
arXiv:2009.14259v2 fatcat:xhlwrmcxergwvcewxpjh7hoox4

Precise but Natural Specification for Robot Tasks [article]

Ivan Gavran, Brendon Boldt, Eva Darulova, Rupak Majumdar
2018 arXiv   pre-print
Flipper starts with a formal core language for task planning that allows expressing rich temporal specifications and uses a semantic parser to provide a natural language interface.  ...  We present Flipper, a natural language interface for describing high-level task specifications for robots that are compiled into robot actions.  ...  Planning and User Interface Given a goal expressed in the core language, Flipper generates an execution plan for the robot to satisfy it in the grid world.  ... 
arXiv:1803.02238v2 fatcat:ttrgntjmsfdrha2p2prwsz3edq

GPT3-to-plan: Extracting plans from text using GPT-3 [article]

Alberto Olmo, Sarath Sreedharan, Subbarao Kambhampati
2021 arXiv   pre-print
Plan extraction methods provide us with the possibility of extracting structure plans from such natural language descriptions of the plans/workflows, which could then be leveraged by an automated system  ...  Despite their criticality to the business, workflows are rarely fully automated or even formally specified, though there may exist a number of natural language documents describing these procedures for  ...  We also want to thank OpenAI and Miles Brundage for letting us get research access to the GPT-3 API.  ... 
arXiv:2106.07131v1 fatcat:xysimyewj5gwnntlwawsopb6gy
« Previous Showing results 1 — 15 out of 811,856 results