Ask Alice: an artificial retrieval of information agent

Valstar, Michel; Baur, Tobias; Cafaro, Angelo; Ghitulescu, Alexandru; Potard, Blaise; Wagner, Johannes; André, Elisabeth; Durieu, Laurent; Aylett, Matthew P.; Dermouche, Soumia; Pélachaud, Catherine; Coutinho, Eduardo; Schuller, Björn; Zhang, Yue; Heylen, Dirk; Theune, Mariët; Waterschoot, Jelte van

doi:10.1145/2993148.2998535

Cited by 18 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It focuses on an informationproviding task between a human user and an embodied conversational agent operated by a Woz. This corpus has been collected as part of the ARIA VALUSPA project which targets multimodal virtual agent for information retrieval that can deal with unexpected situations [61]. The conversational domain of this corpus is the novel Alice's Adventures in Wonderland written by Lewis Carroll.…”

Section: Relationship With the (C)rqa Approachmentioning

confidence: 99%

Towards alignment strategies in human-agent interactions based on measures of lexical repetitions

Duplessis

Langlet²,

Clavel

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

Alignment of communicative behaviour is an important feature of Human-Human interaction that directly affects the collaboration and the social connection of conversational partners. With the aim of improving virtual agent communicative capabilities, and in particular its strategies related to (lexical) verbal alignment, this article focuses on the alignment of linguistic productions of dialogue participants in task-oriented dialogues. We propose a new framework to quantify both the lexical alignment and the self-repetition behaviours of dialogue participants from dyadic dialogue transcripts. It involves easily computable measures based on repetition of lexical patterns automatically extracted via a sequential pattern mining approach. These measures allow the characterisation of the nature of these processes by addressing various informative aspects such as their variety, complexity, and strength. This framework is implemented in the freely available and open-source software dialign. Using these measures, we present a contrastive study between Human-Human and Human-Agent dialogues on various corpora that exposes major differences in the lexical alignment and self-repetition behaviours. Eventually, we address the challenge of integrating lexical alignment capabilities in artificial agents. To this end, we describe guidelines and we discuss the integration of the proposed framework in a real-time dialogue system.

show abstract

Section: Relationship With the (C)rqa Approachmentioning

confidence: 99%

Towards alignment strategies in human-agent interactions based on measures of lexical repetitions

Duplessis

Langlet²,

Clavel

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…In the ARIA-VALUSPA project, a multi-modal information providing agent was developed [25]. Users can ask the agent questions about a specific domain and the agent tells stories to the users.…”

Section: Use-casesmentioning

confidence: 99%

Flipper 2.0

Waterschoot

Bruijnes

Flokstra

et al. 2018

Proceedings of the 18th International Conference on Intelligent Virtual Agents

Self Cite

View full text Add to dashboard Cite

We present a new dialogue engine called Flipper 2.0 (Flipper) which aims to help developers of embodied conversational agents (ECAs) to quickly and flexibly create dialogues. Flipper provides a technically stable and robust dialogue management system to integrate with other components of ECAs such as behaviour realisers. We compare Flipper with state-of-the-art dialogue design systems. We describe the details of our dialogue engine, how it handles dialogue management and how it supports the authoring of dialogues. We demonstrate the use of the dialogue engine with examples of design patterns and discuss practical applications. Finally we give recommendations on the cases in which it is beneficial to use Flipper. CCS CONCEPTS• Human-centered computing → Natural language interfaces; Systems and tools for interaction design; User interface toolkits;• Information systems → Open source software; KEYWORDS dialogue manager, dialogue engine, dialogue design, pragmatics, embodied conversational agent ACM Reference Format:

show abstract

“…Moreover, some assumed the guide was an artificial intelligence because it could 'recognise' the painting the user was situated in front of and started talking to them. The idea that even a simple embodied guide suggests intelligence stands as an indicator that there may be a place for actually intelligent agent-based guides, which could converse more dynamically with the user, such as those virtual humans described in [30].…”

Section: Guide Controlmentioning

confidence: 99%

Appropriate Control Methods for Mobile Virtual Exhibitions

Tennent

Cobb

2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

It is becoming popular to render art exhibitions in Virtual Reality (VR). Many of these are used to deliver at-home experiences on peoples' own mobile devices, however, control options on mobile VR systems are necessarily less flexible than those of situated VR fixtures. In this paper, we present a study that explores aspects of control in such VR exhibitions-specifically comparing 'on rails' movement with 'free' movement. We also expand the concept of museum audio guides to better suit the VR medium, exploring the possibility of embodied characterguides. We compare these controllable guides with a more traditional audio-guide. The study uses interviews to explore users' experience qualitatively, as well as questionnaires addressing both user experience and simulator sickness. The results suggest that users generally prefer to have control over both their movement and the guide, however, if relinquishing movement control, they prefer the uncontrolled guide. The paper presents three key findings: (1) users prefer to be able to directly control their movement; (2) this does not make a notable difference to simulator sickness; (3) embodied guides are potentially a good way to deliver additional information in VR exhibition settings.

show abstract

Ask Alice: an artificial retrieval of information agent

Cited by 18 publications

References 6 publications

Towards alignment strategies in human-agent interactions based on measures of lexical repetitions

Towards alignment strategies in human-agent interactions based on measures of lexical repetitions

Flipper 2.0

Appropriate Control Methods for Mobile Virtual Exhibitions

Contact Info

Product

Resources

About