The Amitiés system: Data-driven techniques for automated dialogue

Hardy, Hilda; Biermann, Alan W.; Inouye, R. Bryce; McKenzie, Ashley; Strzalkowski, Tomek; Ursu, Cristian; Webb, Nick; Wu, Min

doi:10.1016/j.specom.2005.07.006

Cited by 12 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He was not given audio or video of the participant's session so the analysis was based only on the transcribed dialogue. In general, the reviewer (a computer scientist with significant experience in building spoken language dialogue systems [14], [5]) looked at the "style" of the interaction. Dialogues with machines are often shorter (in utterance length and overall length) than comparable conversations with humans, and invoke significantly less use of dysfluencies (such as "er" and "um") and politeness (apologising, for example).…”

Section: Discussionmentioning

confidence: 99%

Wizard of Oz Experiments and Companion Dialogues

Bradley

Benyon

Mival

et al. 2010

Electronic Workshops in Computing

Self Cite

View full text Add to dashboard Cite

Novel speech systems such as the conversational agents being developed by the Companions Project (www.companions-project.org) can be simulated using the Wizard of Oz methodology. In this approach technologies that are not yet ready for testing by people are replaced by a human, both for prototyping and collecting additional dialogue data. In the case of Companions we want to observe what it would be like for people interact with a fully functional embodied conversational agent (ECA) and to collect samples of typical dialogue in order to explore, evaluate and model dialogue strategies. One controversial aspect of the Wizard of Oz approach is whether people should be aware that they are interacting with a simulation or whether they should be "fooled" into thinking they are interacting with a real system. Clearly there are ethical issues involved in fooling people, but some argue that unless the participant believes the simulation to be real, the results of any experimentation will not be applicable to the real situation. Over the course of several previous Wizard of Oz experiments our observations suggest that the dialogues produced do not significantly differ whether the participants know that the technology is faked or not. This hypothesis was investigated by collecting dialogues from two groups of participants. One group of participants believed that the Wizard of Oz speech system was in fact a fully computerised prototype and the other group knew that they would be talking through the interface to a hidden person (the wizard). The dialogues were analysed for differences attributable to the participants' beliefs about the system. This analysis was undertaken by an independent "blind" reviewer, a dialogue expert who attempted to allocate participants to one group or the other. His guess was wrong for four out of the six participants. Thus it appears that whether people believe they are interacting with a real system or not does not effect the dialogues and other factors, for example the personality of the person engaged in a dialogue with an ECA, are more important.

show abstract

Section: Discussionmentioning

confidence: 99%

Wizard of Oz Experiments and Companion Dialogues

Bradley

Benyon

Mival

et al. 2010

Electronic Workshops in Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…One of the most widespread is information retrieval. Some sample applications are tourist and travel information (Glass et al, 1995;Os, Boves, Lamel, & Baggia, 1999), weather forecast (Zue et al, 2000), banking (Hardy et al, 2006;Melin, Sandell, & Ihse, 2001), and conference help (Andreani et al, 2006;Bohus, Raux, Harris, Eskenazi, & Rudnicky, 2007).…”

Section: Sample Applicationsmentioning

confidence: 99%

Review of spoken dialogue systems

López-Cózar

Callejas

Griol

et al. 2014

loquens

View full text Add to dashboard Cite

Spoken dialogue systems are computer programs developed to interact with users employing speech in order to provide them with specific automated services. The interaction is carried out by means of dialogue turns, which in many studies available in the literature, researchers aim to make as similar as possible to those between humans in terms of naturalness, intelligence and affective content.In this paper we describe the fundaments of these systems including the main technologies employed for their development. We also present an evolution of this technology and discuss some current applications. Moreover, we discuss development paradigms, including scripting languages and the development of conversational interfaces for mobile apps.The correct modelling of the user is a key aspect of this technology. This is why we also describe affective, personality and contextual models. Finally, we address some current research trends in terms of verbal communication, multimodal interaction and dialogue management.Keywords: dialogue; language understanding; dialogue management; natural language generation; speech synthesis. RESUMEN:Sistemas de diálogo: una revisión.-Los sistemas de diálogo son programas de ordenador desarrollados para interaccionar con los usuarios mediante habla, con la finalidad de proporcionarles servicios automatizados. La interacción se lleva a cabo mediante turnos de un tipo de diálogo que, en muchos estudios existentes en la literatura, los investigadores intentan que se parezca lo más posible al diálogo real que se lleva a cabo entre las personas en lo que se refiere a naturalidad, inteligencia y contenido afectivo.En este artículo describimos los fundamentos de esta tecnología, incluyendo las tecnologías básicas que se utilizan para implementar este tipo de sistemas. También presentamos una evolución de la tecnología y comentamos algunas aplicaciones actuales. Asimismo, describimos paradigmas de interacción, incluyendo lenguajes de script y desarrollo de interfaces conversacionales para aplicaciones móviles.Un aspecto clave de esta tecnología consiste en realizar un correcto modelado del usuario. Por este motivo, discutimos diversos modelos afectivos, de personalidad y contextuales. Finalmente, comentamos algunas líneas de investigación actuales relacionadas con la comunicación verbal, interacción multimodal y gestión del diálogo.Palabras clave: diálogo; comprensión del lenguaje; gestión del diálogo; generación del lenguaje natural; síntesis del habla.

show abstract

“…One of the most wide-spread is information retrieval. Some sample applications are tourist and travel information [8,14], weather forecast over the phone [23], speech controlled telephone banking systems [12,13], conference help [5,10], etc. They have also been used for education and training, particularly in improving phonetic and linguistic skills: assistance and guidance to F18 aircraft personnel during maintenance tasks [4], dialog applications for computer-aided speech therapy with different language pathologies [2].…”

Section: Case Study Ii: Railway Station Scenariomentioning

confidence: 99%

Multi-agent System (MAS) Applications in Ambient Intelligence (AmI) Environments

Sánchez-Pi

Mangina

Carbó

et al. 2010

Advances in Intelligent and Soft Computing

View full text Add to dashboard Cite

Abstract. Research in context-aware systems has been moving towards reusable and adaptable architectures for managing more advanced human-computer interfaces. Ambient. Intelligence (AmI) investigates computer-based services, which are ubiquitous and based on a variety of objects and devices. Their intelligent and intuitive interfaces act as mediators through which people can interact with the ambient environment. In this paper we present an agent-based architecture which supports the execution of agents in AmI environments. Two case studies are also presented, an airport information system and a railway information system, which uses spoken conversational agents to respond to the user's requests using the contextual information that includes the location information of the user.

show abstract

The Amitiés system: Data-driven techniques for automated dialogue

Cited by 12 publications

References 34 publications

Wizard of Oz Experiments and Companion Dialogues

Wizard of Oz Experiments and Companion Dialogues

Review of spoken dialogue systems

Multi-agent System (MAS) Applications in Ambient Intelligence (AmI) Environments

Contact Info

Product

Resources

About