This paper describes a novel method by which a dialogue agent can learn to choose an optimal dialogue strategy. While it is widely agreed that dialogue strategies should be formulated in terms of communicative intentions, there has been little work on automatically optimizing an agent's choices when there are multiple ways to realize a communicative intention. Our method is based on a combinati...

Argument dialogues provide a principled way of structuring rational interactions between participants (be they human or machine), each arguing over the validity of certain claims, with each agent aiming for an outcome that achieves their dialogue goal (e.g., to persuade the other participant to accept their point of view [8], or to reach agreement on an action to perform [2]). Achievement of an...

We propose a context-sensitive method to predict noun-phrases ill the next utterance of a telephone inquiry dialogue. First, information about tile utterance type and the discourse entities of the next utterance is graspcd using a dialogue interpretation model. Second, a domain-dependent knowledge base for noun-phrase usage is developed , focusing on the dialogue situations in context. Finally,...

In our paper we describe experiences in the eld of linguistic processing for spoken dialogue systems we made during the project Syslid 1. Within Syslid a linguistic component for three diierent domains was developed. We present a development strategy for the creation of linguistic knowledge bases for diierent domains as well as preliminary results achieved in following this strategy.

Information-providing dialogue systems typically use one of the following dialogue strategies: finite-state based, frame-based, or agentbased. Recent extensions are concerned with hybrid models, where mixed automaton and information state approaches are combined. We report on our multimodal mobile Semantic Web access system SMARTWEB which uses a more rigid dialogue management strategy to ensure...

Conversational spoken dialogue systems that interact with the user rather than merely 1 reading text can be equipped with hesitations to manage the dialogue flow and the users’ attention. 2 Based on a series of empirical studies, we built an elaborated hesitation synthesis strategy for 3 dialogue systems that inserts hesitations of scalable extent wherever needed in the ongoing 4 utterance. So ...

In human-human communication, dialogue participants are continuously sending and receiving signals on the status of the information being exchanged. We claim that if spoken dialogue systems were able to detect such cues and change their strategy accordingly, the interaction between user and system would improve. Therefore, the goals of the present study are as follows: (i) to find out which pos...

When people communicate, they coordinate a wide range of linguistic and non-linguistic behaviors. This process of coordination is called alignment, and it is assumed to be fundamental to successful communication. In this paper, we question this assumption and investigate whether disalignment is a more successful strategy in some cases. More specifically, we hypothesize that alignment correlates...

Conversational spoken dialogue systems that interact with the user rather than merely reading the text can be equipped with hesitations to manage dialogue flow and user attention. Based on a series of empirical studies, we elaborated a hesitation synthesis strategy for dialogue systems, which inserts hesitations of a scalable extent wherever needed in the ongoing utterance. Previously, evaluati...

We address two problems in the field of automatic optimization of dialogue strategies: learning effective dialogue strategies when no initial data or system exists, and optimising dialogue management (DM) and Natural Language Generation (NLG) decisions in an integrated fashion. We use Reinforcement Learning (RL) to learn multimodal information presentation strategies through interaction with a ...