Open AccessProceedings Article
PLOW: a collaborative task learning agent
James F. Allen,Nathanael Chambers,George Ferguson,Lucian Galescu,Hyuckchul Jung,Mary Swift,William Taysom +6 more
- pp 1514-1519
TLDR
This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue that integrates a range of AI technologies.Abstract:
To be effective, an agent that collaborates with humans needs to be able to learn new tasks from humans they work with. This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue. To accomplish this, the system integrates a range of AI technologies: deep natural language understanding, knowledge representation and reasoning, dialogue systems, planning/agent-based systems and machine learning. A formal evaluation shows the approach has great promise.read more
Citations
More filters
Proceedings Article
Unsupervised Modeling of Twitter Conversations
TL;DR: This work proposes the first unsupervised approach to the problem of modeling dialogue acts in an open domain, trained on a corpus of noisy Twitter conversations, and addresses the challenge of evaluating the emergent model with a qualitative visualization and an intrinsic conversation ordering task.
Proceedings ArticleDOI
Toward establishing trust in adaptive agents
TL;DR: A study among test users of CALO, one such complex adaptive agent system, concludes that the availability of explanation capabilities in these agents can address the majority of trust concerns identified by users.
Proceedings ArticleDOI
Real-time crowd control of existing interfaces
TL;DR: This paper presents mediation strategies for integrating the input of multiple crowd workers in real-time, evaluates these mediation strategies across several applications, and further validate Legion by exploring the space of novel applications that it enables.
Real-time crowd control of existing interfaces
TL;DR: Legion as discussed by the authors is a system that allows end users to easily capture existing GUIs and outsource them for collaborative, real-time control by the crowd, using mediation strategies for integrating the input of multiple crowd workers.
Proceedings ArticleDOI
SUGILITE: Creating Multimodal Smartphone Automation by Demonstration
TL;DR: This lab study suggests that users with little or no programming knowledge can successfully automate smartphone tasks using SUGILITE.
References
More filters
Proceedings Article
TRIPs: an integrated intelligent problem-solving assistant
George Ferguson,James F. Allen +1 more
TL;DR: How the integrated system provides key advantages for helping both work in natural language dialogue processing and in interactive planning and problem solving is discussed, and the opportunities such an approach affords for the future are considered.
Journal ArticleDOI
Toward Conversational Human-Computer Interaction
James F. Allen,Donna Byron,Myroslava O. Dzikovska,George Ferguson,Lucian Galescu,Amanda Stent +5 more
TL;DR: The results of a 10-year effort building robust spoken dialogue systems at the University of Rochester are described, which show that speech-driven interfaces to computers are starting to appear feasible.
Proceedings ArticleDOI
Learning procedural knowledge through observation
Michael van Lent,John E. Laird +1 more
TL;DR: A framework that provides the necessary infrastructure to learn procedural knowledge from observation traces annotated with goal transition information is described and one instance of a learning-by-observation system, called KnoMic (Knowledge Mimic), is developed and evaluated in a complex domain.
Proceedings ArticleDOI
Programming by demonstration: an inductive learning formulation
Tessa Lau,Daniel S. Weld +1 more
TL;DR: This paper proposes two applicationindependent methods for performing generalization that are based on well-understood machine learning technology, TGenvs uses version-space generalization, and TGenfoil is based on the FOIL inductive logic programming algorithm.
Proceedings ArticleDOI
Sheepdog: learning procedures for technical support
TL;DR: Sheepdog is presented, an implemented system for capturing, learning, and playing back technical support procedures on the Windows desktop using Input/Output Hidden Markov Models and the results of a user study that examines how users follow printed directions.