Extending Conversational Agents for Task-Oriented Human-Computer Dialogue

2011 ◽  
pp. 177-202
Author(s):  
Pierre Andrews ◽  
Silvia Quarteroni
Keyword(s):  
Question Answering ◽  
A Priori ◽  
Conversational Agents ◽  
Complex Tasks ◽  
Explicit Formulation ◽  
Lead Users ◽  
Interactive Question ◽  
Task Oriented

We present the role of conversational agents in two task-oriented human-computer dialogue applications: Interactive Question Answering and Persuasive Dialogue. We show that conversational agents can be effectively deployed for interaction that goes beyond user entertainment and can be successfully used as a means to achieve complex tasks. Conversational agents are a winning solution in Persuasive Dialogue because, combined with a planning infrastructure, they can help manage the parts of the dialogue that cannot be planned a priori and are primordial to keep the system persuasive. In Interactive Question Answering, conversational approaches lead users to the explicit formulation of queries, allow for the submission of further queries and accomodate related queries thanks to their ability to handle context.

Understanding automated conversational agent as a decision aid: matching agent's conversation with customer's shopping task

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jengchung Victor Chen ◽  
Huyen Thi Le ◽  
Sinh Thi Thu Tran
Keyword(s):  
Decision Aid ◽  
Performance Outcomes ◽  
Communication Style ◽  
Conversational Agents ◽  
Information Presentation ◽  
Cognitive Fit ◽  
Content Type ◽  
Cognitive Fit Theory ◽  
Task Oriented

PurposeTo provide better services to customers, especially immediate responses and 24/7 availability, businesses are implementing text-based automated conversational agents, i.e. chatbots on their social platforms and websites. Chatbots are required to not only provide customers with necessary consultancy and guidance but also communicate friendly and socially. Based on the cognitive fit theory, this study attempts to examine the role of chatbot as a decision aid and how the match between information presentation in forms of decisional guidance and communication style and the shopping task influences consumers' perceived cognitive fit and decision performance outcomes.Design/methodology/approachA 2 x 2 x 2 between subject online experiment was conducted to identify which kind of decisional guidance (suggestive and informative guidance) and communication style (task-oriented vs social-oriented style) are the most appropriate for each type of shopping task (searching vs browsing task).FindingsThe findings show that when customers interact with chatbots, they will perceive higher cognitive fit if the chatbots provide them with suggestive guidance and communicate in a friendly style especially when they perform a searching task.Originality/valueThis study is the first attempt to understand the role of chatbots as a decision aid to customers using the communicative language. This study also tries to explore the cognitive fit theory in a novel way, and we propose the information presentation in forms of communicative language rather than matrices, tables and graphs.

Collection of Ego-Centered Network Data with Computer-Assisted Interviews

Methodology ◽  
2006 ◽  
Vol 2 (1) ◽  
pp. 7-15 ◽  
Author(s):  
Joachim Gerich ◽  
Roland Lehner
Keyword(s):  
Survey Methods ◽  
A Priori ◽  
Dynamic Structure ◽  
Computer Assisted ◽  
Network Data ◽  
Great Effort ◽  
Self Administration ◽  
Face To Face ◽  
Full Network

Although ego-centered network data provide information that is limited in various ways as compared with full network data, an ego-centered design can be used without the need for a priori and researcher-defined network borders. Moreover, ego-centered network data can be obtained with traditional survey methods. However, due to the dynamic structure of the questionnaires involved, a great effort is required on the part of either respondents (with self-administration) or interviewers (with face-to-face interviews). As an alternative, we will show the advantages of using CASI (computer-assisted self-administered interview) methods for the collection of ego-centered network data as applied in a study on the role of social networks in substance use among college students.

Disrupted Salience and Cingulo-Opercular Network Connectivity During Impaired Rapid Instructed Task Learning in Schizophrenia

2021 ◽  
pp. 216770262095934
Author(s):  
Julia M. Sheffield ◽  
Holger Mohr ◽  
Hannes Ruge ◽  
Deanna M. Barch
Keyword(s):  
A Priori ◽  
Network Connectivity ◽  
Task Learning ◽  
Human Ability ◽  
Functional Brain Networks ◽  
Task Goals ◽  
Multivariate Pattern ◽  
And Control ◽  
Goal Directed Behavior

Rapid instructed task learning (RITL) is the uniquely human ability to transform task information into goal-directed behavior without relying on trial-and-error learning. RITL is a core cognitive process supported by functional brain networks. In patients with schizophrenia, RITL ability is impaired, but the role of functional network connectivity in these RITL deficits is unknown. We investigated task-based connectivity of eight a priori network pairs in participants with schizophrenia ( n = 29) and control participants ( n = 31) during the performance of an RITL task. Multivariate pattern analysis was used to determine which network connectivity patterns predicted diagnostic group. Of all network pairs, only the connectivity between the cingulo-opercular network (CON) and salience network (SAN) during learning classified patients and control participants with significant accuracy (80%). CON-SAN connectivity during learning was significantly associated with task performance in participants with schizophrenia. These findings suggest that impaired interactions between identification of salient stimuli and maintenance of task goals contributes to RITL deficits in participants with schizophrenia.

scholarly journals The Role of Global Appearance of Omnidirectional Images in Relative Distance and Orientation Retrieval

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3327
Author(s):  
Vicente Román ◽  
Luis Payá ◽  
Adrián Peidró ◽  
Mónica Ballesta ◽  
Oscar Reinoso
Keyword(s):  
Mobile Robotics ◽  
A Priori ◽  
Computational Cost ◽  
Relevant Information ◽  
Local Features ◽  
New Family ◽  
Lighting Conditions ◽  
Omnidirectional Images ◽  
Great Development

Over the last few years, mobile robotics has experienced a great development thanks to the wide variety of problems that can be solved with this technology. An autonomous mobile robot must be able to operate in a priori unknown environments, planning its trajectory and navigating to the required target points. With this aim, it is crucial solving the mapping and localization problems with accuracy and acceptable computational cost. The use of omnidirectional vision systems has emerged as a robust choice thanks to the big quantity of information they can extract from the environment. The images must be processed to obtain relevant information that permits solving robustly the mapping and localization problems. The classical frameworks to address this problem are based on the extraction, description and tracking of local features or landmarks. However, more recently, a new family of methods has emerged as a robust alternative in mobile robotics. It consists of describing each image as a whole, what leads to conceptually simpler algorithms. While methods based on local features have been extensively studied and compared in the literature, those based on global appearance still merit a deep study to uncover their performance. In this work, a comparative evaluation of six global-appearance description techniques in localization tasks is carried out, both in terms of accuracy and computational cost. Some sets of images captured in a real environment are used with this aim, including some typical phenomena such as changes in lighting conditions, visual aliasing, partial occlusions and noise.

scholarly journals Visualization approaches to support healthy aging: A systematic review

2016 ◽  
Vol 23 (3) ◽  
pp. 600 ◽  
Author(s):  
Uba Backonja ◽  
Nai-Ching Chi ◽  
Yong Choi ◽  
Amanda K Hall ◽  
Thai Le ◽  
...  
Keyword(s):  
Older Adults ◽  
Health Behaviors ◽  
Healthy Aging ◽  
A Priori ◽  
Aging In Place ◽  
Future Research ◽  
Health Technologies ◽  
Data Visualizations ◽  
Informatics Tools

Background: Health technologies have the potential to support the growing number of older adults who are aging in place. Many tools include visualizations (data visualizations, visualizations of physical representations). However, the role of visualizations in supporting aging in place remains largely unexplored.Objective: To synthesize and identify gaps in the literature evaluating visualizations (data visualizations and visualizations of physical representations), for informatics tools to support healthy aging.Methods: We conducted a search in CINAHL, Embase, Engineering Village, PsycINFO, PubMed, and Web of Science using a priori defined terms for publications in English describing community-based studies evaluating visualizations used by adults aged ≥65 years.Results: Six out of the identified 251 publications were eligible. Most studies were user studies and varied methodological quality. Three visualizations of virtual representations supported performing at-home exercises. Participants found visual representations either (a) helpful, motivational, and supported their understanding of their health behaviors or (b) not an improvement over alternatives. Three data visualizations supported understanding of one’s health. Participants were able to interpret data visualizations that used precise data and encodings that were more concrete better than those that did not provide precision or were abstract. Participants found data visualizations helpful in understanding their overall health and granular data.Conclusions: Studies we identified used visualizations to promote engagement in exercises or understandings of one’s health. Future research could overcome methodological limitations of studies we identified to develop visualizations that older adults could use with ease and accuracy to support their health behaviors and decision-making.

scholarly journals Family quarrels in seeds and rapid adaptive evolution in Arabidopsis

2019 ◽  
Vol 116 (19) ◽  
pp. 9463-9468 ◽  
Author(s):  
Katherine S. Geist ◽  
Joan E. Strassmann ◽  
David C. Queller
Keyword(s):  
Adaptive Evolution ◽  
Kin Selection ◽  
Conflicts Of Interest ◽  
A Priori ◽  
Flowering Plant ◽  
Rapid Adaptation ◽  
Arms Races ◽  
Evolutionary Conflict ◽  
Alternative Hypotheses

Evolutionary conflict can drive rapid adaptive evolution, sometimes called an arms race, because each party needs to respond continually to the adaptations of the other. Evidence for such arms races can sometimes be seen in morphology, in behavior, or in the genes underlying sexual interactions of host−pathogen interactions, but is rarely predicted a priori. Kin selection theory predicts that conflicts of interest should usually be reduced but not eliminated among genetic relatives, but there is little evidence as to whether conflict within families can drive rapid adaptation. Here we test multiple predictions about how conflict over the amount of resources an offspring receives from its parent would drive rapid molecular evolution in seed tissues of the flowering plant Arabidopsis. As predicted, there is more adaptive evolution in genes expressed in Arabidopsis seeds than in other specialized organs, more in endosperms and maternal tissues than in embryos, and more in the specific subtissues involved in nutrient transfer. In the absence of credible alternative hypotheses, these results suggest that kin selection and conflict are important in plants, that the conflict includes not just the mother and offspring but also the triploid endosperm, and that, despite the conflict-reducing role of kinship, family members can engage in slow but steady tortoise-like arms races.

The Role of Dimensional Distinctiveness in Children's and Adults' Artifact Categorization

2005 ◽  
Vol 16 (2) ◽  
pp. 137-144 ◽  
Author(s):  
Rubi Hammer ◽  
Gil Diesendruck
Keyword(s):  
Preschool Children ◽  
Contextual Factors ◽  
A Priori ◽  
Functional Similarity ◽  
Second Stage ◽  
Functional Dimension

There are conflicting results as to whether preschool children categorize artifacts on the basis of physical or functional similarity. The present study investigated the effect of the relative distinctiveness of these dimensions in children's categorization. In a physical-distinctive condition, preschool children and adults were initially asked to categorize computer-animated artifacts whose physical appearances were more distinctive than their functions. In a function-distinctive condition, the functional dimension of objects was more distinctive than their physical appearances. Both conditions included a second stage of categorization in which both dimensions were equally distinctive. Participants in a control condition performed only this stage of categorization. Adults in all conditions and stages consistently categorized by functional similarity. In contrast, children's categorization was affected by the relative distinctiveness of the dimensions. Children may not have a priori specific beliefs about how to categorize novel artifacts, and thus may be more susceptible to contextual factors.

Multiple boundary blow-up solutions for nonlinear elliptic equations

2003 ◽  
Vol 133 (2) ◽  
pp. 225-235 ◽  
Author(s):  
Amandine Aftalion ◽  
Manuel del Pino ◽  
René Letelier
Keyword(s):  
Elliptic Equations ◽  
Blow Up ◽  
A Priori ◽  
Nonlinear Elliptic Equations ◽  
Positive Parameter ◽  
Number Of Solutions ◽  
Bounded Smooth Domain ◽  
Nonlinear Elliptic ◽  
Bounded Smooth

We consider the problem Δu = λf(u) in Ω, u(x) tends to +∞ as x approaches ∂Ω. Here, Ω is a bounded smooth domain in RN, N ≥ 1 and λ is a positive parameter. In this paper, we are interested in analysing the role of the sign changes of the function f in the number of solutions of this problem. As a consequence of our main result, we find that if Ω is star-shaped and f behaves like f(u) = u(u−a)(u−1) with ½ < a < 1, then there is a solution bigger than 1 for all λ and there exists λ0 > 0 such that, for λ < λ0, there is no positive solution that crosses 1 and, for λ > λ0, at least two solutions that cross 1. The proof is based on a priori estimates, the construction of barriers and topological-degree arguments.

Sign in / Sign up

Export Citation Format

Share Document