Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn

of utterances in human dialogues that, prima facie, appear inefficient, and provide the basis for the design of effective algorithms for communicative choice for resource limited agents.

1 Abstract: Sentence similarity measures play an increasingly important role in textrelated research and applications in areas such as text mining, web page retrieval and dialogue systems. Existing methods for computing sentence similarity have been adopted from approaches used for long text

EasyNav is a Chinese spoken language dialogue system for campus navigation that we introduced at ICSLP2000 [1]. Recently, we have initiated a significant redesign of some modules to make it resolve some inefficient problem in EasyNav, such as analysis of complex sentences, context processing

Electronic financial news available on the Internet contains a wealth of information useful for business decision-making. However, as this information is both qualitative and existent in huge volumes, it is very inefficient to digest manually. This paper presents a prototype system called FNDS

A major problem faced by developers of spoken language dialogue systems and other language engineering products concerns the re-use of corpora or tools in different development or customisation projects. So far, most projects have had to either develop the necessary resources from scratch

Builders of spoken dialogue systems are always faced with a dilemma. For simple tasks, they can hand-craft an efficient and robust parser for the system, but the technique does not generalize and is not very portable to new tasks. On the other hand, parsing with linguistically

In order for a model of rational agency to be used for multi-agent social interaction, the model must be extended to account for communicative behaviors that are inefficient for one agent, but which increase the efficiency of the interaction of two agents in a dialogue. In this paper, we argue

Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogues presents special challenges. To model the conversational dynamics of concurrent chatting behaviors, this paper

, there are groups that criticize the inefficiency of the State, putting the supremacy of the marketas potential substitutes of the State. The political action of these organizations, characterized by dialogue, mobilization, participation, that is aiming at qualification of the state, the accountability of public