This paper deals with the automatic analysis of conversations between a customer and an agent in a call centre of a customer care service. The purpose of the analysis is to hypothesize themes about problems and complaints discussed in the conversation. Themes are defined by the application documentation topics. A conversation may contain mentions that are irrelevant for the application purpose ...

The main aim of this research is to investigate a novel technique for implementing a more natural and intelligent conversation system. Conversation systems are designed to converse like a human as much as their intelligent allows. Sometimes, we can think that they are the embodiment of Turing’s vision. It usually to return a predetermined answer in a predetermined order, but conversations aboun...

Mixed-initiative interaction (MII) plays an important role in conversation agent. In the former MII research, MII process only static conversation and cannot change the conversation topic dynamically by the system because the agent depends only on the working memory and predefined methodology. In this paper, we propose the mixed-initiative interaction based on human cognitive architecture and m...

Speaker diarization systems attempt segmentation and labeling of a conversation between R speakers, while no prior information is given regarding the conversation. Most state of the art diarization systems require the full body of the conversation data prior to the application of some diarization approach. However, for some applications such as forensics, which handles vast amount of data, an o...

With the goal of designing conversational agents that can join and manage conversations with multiple participants, in this paper, we conduct an experiment to collect multiparty conversations with a virtual agent, and recognize head direction as each participant’s focus of attention. Then, we analyze how gaze and mutual gaze affect floor management and conversation dominance; we assumed that th...

We show that participants in conversation develop beliefs about shared information that others do not. So-called directors talked with two partners in succession (A and B) to arrange unusual figures. Directors went from long, indefinite descriptions of the figures to short, definite references as common ground was built up with A. When B had been a silent side participant in the fast conversati...

Although the notion of conversations has been discussed for some time as a way in which to provide an abstract representation of extended agent message exchange, there is still no consensus established concerning how to use these abstractions effectively. This paper describes a layered approach based on coloured Petri Nets that can be used for modelling complex, concurrent conversations among a...

While a significant amount of research has been devoted to textual entailment, automated entailment from conversational scripts has received less attention. To address this limitation, this paper investigates the problem of conversation entailment: automated inference of hypotheses from conversation scripts. We examine two levels of semantic representations: a basic representation based on synt...

In this talk, we introduce a robot conversation system. Generally speaking, the conversation is not performed only through the exchange of speech information. It needs the exchange of visual information: facial expressions, body poses, and gestures convey rich information to achieve natural conversation. In this context, the body and the vision system of the robot, can be regard as the essentia...

Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue....