A prototype for a conversational companion for reminiscing about images

Wilks, Yorick; Catizone, Roberta; Worgan, Simon F.; Dingli, Alexiei; Moore, Roger K.; Field, Debora; Cheng, Weiwei

doi:10.1016/j.csl.2010.04.002

Cited by 19 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather than modelling language itself as represented by a corpus, our approach models the language production process. This has been criticised by Wilks for only doing "one half of dialogue" (the non user's half) [30] but this is indeed how much of linguistics views the process. Our approach is theoretically well-founded, not in mathematics, but in linguistics.…”

Section: Further Workmentioning

confidence: 99%

Using Agents in Virtual Environments to Assist Controllers to Manage Multiple Assets

Beer

Alboul

Norling

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Search and rescue operations often require complex coordination of a range of resources, including human and robotic resources. This paper discusses a proposed new framework that allows agent technology to be used in conjunction with a virtual environment to provide a human controller with an effective visualisation of the distribution of a collection of autonomous objects, in our case, Unmanned Aerial Vehicles (UAVs) so that they can be managed in a way that allows them to successfully complete the task in the minimum possible time. It is our contention that to do this effectively there needs to be two-way initiation of verbal conversations, but that it is not necessary for the system to completely understand the conversations required. An example scenario is presented that illustrates how such a system would be used in practice, illustrating how a single human can verbally communicate with a swarm of semi-autonomous actors verbally and envisage their activities in a swarm based on the visual cues provided within the virtual environment. An agent-based solution is proposed that meets the requirements and provides an effective command station that can manage a search using a collection of UAVs effectively.

show abstract

Section: Further Workmentioning

confidence: 99%

Using Agents in Virtual Environments to Assist Controllers to Manage Multiple Assets

Beer

Alboul

Norling

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…On the contrary, chat-oriented dialogue systems, which can engage in small talk, have been built so that users will enjoy conversations with them Wilks et al, 2011;. It has been tried to combine chat-oriented dialogue systems with taskoriented dialogue systems (Traum et al, 2005;Nakano et al, 2006;Lee et al, 2006).…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

We extend special thanks to our Local co-Chairs, Ron Artstein and Alesia Gainer, and their team of student volunteers. We know SIGDIAL 2016 would not have been possible without Ron and Alesia, who invested so much effort in arranging the conference venue and accommodations, handling registration, making banquet arrangements, and handling numerous other preparations for the conference. The student volunteers for on-site assistance also deserve our appreciation.Ethan Selfridge, Sponsorships Chair, has earned our appreciation for recruiting and liaising with our conference sponsors, many of whom continue to contribute year after year. Sponsorships support valuable aspects of the program, such as the invited speakers and conference banquet. In recognition of this, we gratefully acknowledge the support of our sponsors: (Platinum level) Microsoft Research, Xerox and PARC, Intel, (Gold level) Facebook, (Silver level) Amazon Alexa, Interactions, Educational Testing Service, Honda Research Institute, and Yahoo!. At the same time, we thank Priscilla Rasmussen at the ACL for tirelessly handling the financial aspects of sponsorship for SIGDIAL 2016, and for securing our ISBN.iii We also thank the SIGdial board, especially officers Amanda Stent, Jason Williams and Kristiina Jokinen for their advice and support from beginning to end.Finally, we thank all the authors of the papers in this volume, and all the conference participants for making this stimulating event a valuable opportunity for growth in the research areas of discourse and dialogue. AbstractThis paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent QNetworks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state. IntroductionTask-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003). The SDS agent has to achieve some predefined targets (e.g. booking a flight) through natural language interaction with the users. The typical structure of a task-oriented dialog system is outlined in Figure 1 (Young, 2006). This pipeline consists of several independently-developed modules: natural language understanding (the NLU) maps the user utterances to some semantic representation. This information is further processed by the dialog state tracker (DST), which accumulates the input of the turn along with the dialog history. The DST outputs the current dialog state and the dialog policy selects the next system action based on the dialog state. Then natural language gene...

show abstract

“…On the contrary, chat-oriented dialogue systems, which can engage in small talk, have been built so that users will enjoy conversations with them (Wallace, 2008;Wilks et al, 2011;Higashinaka et al, 2014). It has been tried to combine chat-oriented dialogue systems with taskoriented dialogue systems (Traum et al, 2005;Nakano et al, 2006;Lee et al, 2006).…”

Section: Related Workmentioning

confidence: 99%

Small Talk Improves User Impressions of Interview Dialogue Systems

Kobori¹,

Nakano²,

Nagaoka³

2016

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

This paper addresses the problem of how to build interview systems that users are willing to use. Existing interview dialogue systems are mainly focused on obtaining information from users, thus they just repeatedly ask questions. We propose a method for improving user impressions by engaging in small talk during interviews. The system performs framebased dialogue management for interviewing and generates small talk utterances after the user answers the system's questions. Experimental results using a textbased interview dialogue system for diet recording showed the proposed method gives a better impression to users than interview dialogues without small talk. It is also found that generating too many small talk utterances makes user impressions worse because of the system's low capability of continuously generating appropriate small talk utterances.

show abstract

A prototype for a conversational companion for reminiscing about images

Cited by 19 publications

References 22 publications

Using Agents in Virtual Environments to Assist Controllers to Manage Multiple Assets

Using Agents in Virtual Environments to Assist Controllers to Manage Multiple Assets

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Small Talk Improves User Impressions of Interview Dialogue Systems

Contact Info

Product

Resources

About