233,520 Hits in 3.4 sec

BERT for Conversational Question Answering Systems Using Semantic Similarity Estimation

Abdulaziz Al-Besher, Kailash Kumar, M. Sangeetha, Tinashe Butsa
2022 Computers Materials & Continua  
The model then infers past contextual data related to the given question and predicts an answer based on the context inferred without engaging in multi-turn interactions or requesting additional data from  ...  Most of the questions from users lack the context needed to thoroughly understand the problem at hand, thus making the questions impossible to answer.  ...  Proposed Methodology Problem Statement Given a question q i from the user, the task is to relate q i with CS from past sessions to find and infer past conversational context c k i to q i based on the  ... 
doi:10.32604/cmc.2022.021033 fatcat:wm34anpztzhm5k7q4di2jsxkyi

Machine Learning for User Learning

Janina Schuhmacher
2017 Mensch & Computer  
Drawing on event segmentation theory and knowledge space theory, we propose to model the users' domain specific knowledge and their learning process dynamically in the interaction between system and user  ...  Using case-based reasoning as a psychologically inspired machine learning method facilitates incorporating the user's feedback in the interaction: the system continuously updates its user model to learn  ...  Does the User Need Assistance? Adapt the 2. What Is the Interaction Individual User Profile à User's Knowledge Fringe Adequate Case from the Case Base?  ... 
doi:10.18420/muc2017-up-0127 dblp:conf/mc/Schuhmacher17 fatcat:6wocly3n7bfxpg3vfkf7qxs7me

AAAI-2002 Fall Symposium Series

Yukio Ohsawa, Peter McBurney, Simon Parsons, Christopher A. Miller, Alan C. Schultz, Jean Scholtz, Michael A. Goodrich, Eugene Santos Jr., Benjamin Bell, Charles Lee Isbell Jr., Michael L. Littman
2003 The AI Magazine  
We also talked about exploration, amplification, articulation, interaction, scenic information, subjectivity, and meaning." "Hmmm, you considered the deepening of thoughts.  ...  The symposium addressed work in intent inference that has shed much light on how automation systems can be given some measure of understanding of their users' tasks and needs.  ...  transferred from related tasks), and the initiator of this exchange (the agent, the user, or some combination).  ... 
doi:10.1609/aimag.v24i1.1693 dblp:journals/aim/OhsawaMPMSSGSBIL03 fatcat:ha2vk2fqivf7lc3mqfd7id5any

Adaptive systems: from intelligent tutoring to autonomous agents

D. Benyon, D. Murray
1993 Knowledge-Based Systems  
Computer systems which can automatically alter aspects of their functionality or interface to suit the needs of individuals or groups of users have appeared over the years in a variety of guises.  ...  Most recently attention has focused on intelligent interface agents which are seen as specialised, knowledge-based systems acting on behalf of the user in some aspect of the interaction.  ...  Knowledge for the user model can be acquired implicitly by making inferences about users from their interaction, by carrying out some from of test, or from assigning users to generic user categories usually  ... 
doi:10.1016/0950-7051(93)90012-i fatcat:kqlhiphcvvhatpffz2zalydxni

Steps to take before intelligent user interfaces become real

K. Höök
2000 Interacting with computers  
Unfortunately, there are a number of problems not yet solved that prevent us from creating good intelligent user interface applications: there is a need for methods for how to develop them; there are demands  ...  on better usability principles for them; we need a better understanding of the possible ways the interface can utilise intelligence to improve the interaction; and finally, we need to design better tools  ...  neither stable nor easy to infer from users' interactions with the system.  ... 
doi:10.1016/s0953-5438(99)00006-5 fatcat:6dgas534qfg4zlkykkx7xe6lmq

Communicating Inferred Goals with Passive Augmented Reality and Active Haptic Feedback [article]

James F. Mullen Jr, Josh Mosier, Sounak Chakrabarti, Anqi Chen, Tyler White, Dylan P. Losey
2021 arXiv   pre-print
We apply our system to shared autonomy tasks where the robot must infer the human's goal in real-time.  ...  Robots learn as they interact with humans.  ...  ii) reduces the amount of time users spend monitoring the robot, and iii) improves user teaching so that the robot infers what the human wants from fewer interactions.  ... 
arXiv:2109.01747v1 fatcat:axrhg6245zejpeqdwpxc5xrvru

Communicating Robot Conventions through Shared Autonomy [article]

Ananth Jonnavittula, Dylan P. Losey
2022 arXiv   pre-print
When humans control robot arms these robots often need to infer the human's desired task.  ...  Across repeated interactions the robot intervenes and exaggerates the arm's motion to demonstrate more efficient inputs while also assisting for the current task.  ...  Recall that the human has a specific task that they want to accomplish, and the robot needs to infer that task.  ... 
arXiv:2202.11140v2 fatcat:kvfv22wngrfcbmnkajh6k5mp64

Recommending knowledgeable people in a work-integrated learning system

Günter Beham, Barbara Kump, Tobias Ley, Stefanie Lindstaedt
2010 Procedia Computer Science  
Such agents are observing user interactions (e.g. keystrokes, mouse movements, applications specific actions) and compare them to previously learned interaction patterns.  ...  In order to provide the expert finding functionality, an underlying user model is needed that represents the characteristics of each individual user.  ...  Thus, in APOSDLE, knowledge and skills of the users should be inferred from different types of user interactions with the system.  ... 
doi:10.1016/j.procs.2010.08.003 fatcat:wbmgmqad5rdb7mwewat5kref44

Evaluation of a spatial language interpretation framework for natural human-robot interaction with older adults

Juan Fasola, Maja J. Mataric
2015 2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)  
target users, achieving high task success rates and high participant evaluations across multiple measures.  ...  We present the design and analysis of a multisession user study conducted with older adults to evaluate the effectiveness of a human-robot interaction (HRI) framework utilizing a neuroscience-inspired  ...  To achieve these types of tasks, autonomous service robots will need to be capable of interacting with and learning from non-expert users in a manner that is both natural and practical for the users.  ... 
doi:10.1109/roman.2015.7333611 dblp:conf/ro-man/FasolaM15 fatcat:alf5g7lumrfxrikuv2ejgpyipy

Supporting mixed initiative human-robot interaction: A script-based cognitive architecture approach

Hogun Park, Yoonjung Choi, Yuchul Jung, Sung-Hyon Myaeng
2008 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)  
Starting fr of user initiatives, our intelligent task m most relevant initiatives for an efficient has been evaluated in real indoor tas efficacy in interaction reduction, error m satisfaction.  ...  As complex indoor-robot sy and deployed into the real-world, human-robot interaction is increasin human-robot interaction is a good m actions of a human and a robot in a com In order to support such interactions  ...  If the probability of a task is not high enough to be the current task, the robot interacts with the user.  ... 
doi:10.1109/ijcnn.2008.4634389 dblp:conf/ijcnn/ParkCJM08 fatcat:rirmcaxzhbh6rbcgl5bk7k3ici

Adaptive systems: A solution to usability problems

David Benyon
1993 User modeling and user-adapted interaction  
Improving the usability of computer systems is perhaps the most important goal of human-computer interaction research.  ...  Self-regulating adaptive systems require inference and evaluation mechanisms since they have to learn from interacting with the environment.  ...  Model Interaction Model The interaction model defines the data which the system will obtain from the interaction (the dialogue record) and the inferences, adaptations and evaluations which the system  ... 
doi:10.1007/bf01099425 fatcat:nhz53ed3lvaehhvkj2cg3lk2fu

Using shared representations to improve coordination and intent inference

Joshua Introne, Richard Alterman
2006 User modeling and user-adapted interaction  
First, we show how information that is made available by a coordinating representation can be used to infer user intentions.  ...  Empirical data shows that an automatic plan generation component, which is driven by information from a coordinating representation, reduces coordination errors and cognitive effort for its users.  ...  Some user-adaptive systems infer user's needs by monitoring their task interaction alone. These systems contain few or no meta-language operators (Figure 12 ).  ... 
doi:10.1007/s11257-006-9009-2 fatcat:j4564iso45crjivwg5uykh3a6m

Using ensembles of decision trees to automate repetitive tasks in web applications

Zachary Bray, Per Ola Kristensson
2010 Proceedings of the 2nd ACM SIGCHI symposium on Engineering interactive computing systems - EICS '10  
However, many of the tasks that users try to accomplish with such web applications are highly repetitive.  ...  Our system infers users' intentions using an ensemble of decision trees. This enables it to handle branching, generalization and recurrent changes of relative and absolute positions.  ...  The following applies to P.O.K. only: The research leading to these results has received funding from the European Community's Seventh Framework Programme FP7/2007 2013 under grant agreement number 220793  ... 
doi:10.1145/1822018.1822025 dblp:conf/eics/BrayK10 fatcat:g2ncwsomkvbrbgi6p5mxfuerji

Getting to Know Your User – Unobtrusive User Model Maintenance within Work-Integrated Learning Environments [chapter]

Stefanie N. Lindstaedt, Günter Beham, Barbara Kump, Tobias Ley
2009 Lecture Notes in Computer Science  
; on the other hand users do interact with a multitude of different work applications -there is no central learning system.  ...  Work-integrated learning (WIL) poses unique challenges for user model design: on the one hand users' knowledge levels need to be determined based on their work activities -testing is not a viable option  ...  Interaction of APOSDLE user model and user model services with APOSDLE client Applications As one of the most important inference services the learning need service allows computing a learning need for  ... 
doi:10.1007/978-3-642-04636-0_9 fatcat:lrq7pzit5beujfucbsobpapppq

Interpretable Machine Learning for Privacy-Preserving Pervasive Systems [article]

Benjamin Baron, Mirco Musolesi
2019 arXiv   pre-print
Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users.  ...  In this paper, we propose a machine learning interpretability framework that enables users to understand how these generated traces violate their privacy.  ...  from the interaction with pervasive systems.  ... 
arXiv:1710.08464v6 fatcat:fv66extdtzf65ofz7amyjwhdqq
« Previous Showing results 1 — 15 out of 233,520 results