Introducing ADELE: a personalized intelligent companion

@article{Spillane2017IntroducingAA,
  title={Introducing ADELE: a personalized intelligent companion},
  author={Brendan Spillane and Emer Gilmartin and Christian Saam and Ketong Su and Benjamin R. Cowan and S{\'e}amus Lawless and Vincent P. Wade},
  journal={Proceedings of the 1st ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents},
  year={2017}
}
  • Brendan Spillane, E. Gilmartin, V. Wade
  • Published 13 November 2017
  • Computer Science
  • Proceedings of the 1st ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents
This paper introduces ADELE, a Personalized Intelligent Compan- ion designed to engage with users through spoken dialog to help them explore topics of interest. The system will maintain a user model of information consumption habits and preferences in order to (1) personalize the user’s experience for ongoing interactions, and (2) build the user-machine relationship to model that of a friendly companion. The paper details the overall research goal, existing progress, the current focus, and the… 
Detecting Domain-specific Information needs in Conversational Search Dialogues
TLDR
It is found that a reasonable accuracy in predicting information need categories is possible and evidence the importance of stopwords in the classfication task.
“What Can I Cook with these Ingredients?” - Understanding Cooking-Related Information Needs in Conversational Search
TLDR
A detailed hierarchical taxonomy of diverse information needs occurring in a home cooking context is derived, concluding that models need to include more context information in order to improve both information need classification and assistance to make such systems usable.
Eliciting and Analysing Users’ Envisioned Dialogues with Perfect Voice Assistants
TLDR
A dialogue elicitation study to assess how users envision conversations with a perfect voice assistant (VA), where the majority envisioned dialogues with a VA that is interactive and not purely functional; it is smart, proactive, and has knowledge about the user.
ADELE: Evaluating and Benchmarking an Artificial Conversational Care Agent
TLDR
An overview of a planned experiment to evaluate the latest iteration of ADELE, an artificial conversational agent to aid in the care of the elderly, against an earlier iteration of itself and against the leading systems from the 2018 ConvAI2 Challenge at NeurIPS to measure its progress on producing improved natural social dialogue.
Kiro: A Design Fiction to Explore Social Conversation with Voice Assistants
TLDR
A design fiction of an in-vehicle sVA called Kiro is presented to create a convincing near-future vision of an sVA and to empirically explore its possibilities and challenges.
What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents
TLDR
Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have.
A conversational agent system for dietary supplements use
TLDR
This study develops the first conversational agent system for DS use using MindMeld and iDISK domain knowledge and achieves an overall accuracy of 81% (topmost level Question classification) and an average score of 1.82.
On the Impact of Voice Encoding and Transmission on the Predictions of Speaker Warmth and Attractiveness
TLDR
This article addresses a binary classification of high versus low warm--attractive speakers over different channel and encoding conditions and shows that, under the considered conditions, the AMR-WB+ codec permits good levels of classification accuracy, comparable to the classification with clean, non-degraded speech.
Pilot Data Collection Survey and Analytical Techniques for Persuasion Engineering Systems
TLDR
A pilot survey, and data analysis techniques, designed to inform the development of a larger follow on experiment to predict the most effective form of argumentation based on user characteristics are detailed.
Kiro
Soon, voice assistants might be able to engage in fully-fledged social conversations with people, rather than merely providing a voice-operated interface to functionality and data. So far, not much
...
...

References

SHOWING 1-8 OF 8 REFERENCES
The Second Dialog State Tracking Challenge
TLDR
The results suggest that while large improvements on a competitive baseline are possible, trackers are still prone to degradation in mismatched conditions and ensemble learning demonstrates the most accurate tracking can be achieved by combining multiple trackers.
The third Dialog State Tracking Challenge
TLDR
Results from the third Dialog State Tracking Challenge are presented, a research community challenge task based on a corpus of annotated logs of human-computer dialogs, with a blind test set evaluation that studied the ability of trackers to generalize to new entities - i.e. new slots and values not present in the training data.
Neural Machine Translation by Jointly Learning to Align and Translate
TLDR
It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
2010
Le quorum n’ayant pas été atteint le 16 août 2010, le Conseil Général s’est réuni de plein droit à l’H ôtel du Conseil Général le 19 août 2010 sous la présidence de Monsieur Bernard DEROSIER,
CUED Standard Dialogue Acts
  • Technical Report
  • 2007
Annotation of Greeting and Leave-taking in Social Text Dialogues Using ISO 24617-2
  • In Thirteenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation
  • 2017