We present an approach for the development of a dialog manager based on stochastic models for the representation of the dialogue structure and strategy. This dialog manager processes semantic representations and, when it is integrated with our understanding and answer generation modules, it performs natural language dialogs. It has been applied to a Spanish dialogue system which answers telepho...

Spoken dialogue systems have strong potentiality in becoming the main stream of next generation man/machine interface. To meet this future, spoken dialogue systems must not only be portable to support various applications, but also be scalable to provide capable dialogue to handle sophisticated services. In this paper, we proposed a goal-oriented table-driven approach to design a portable and s...

For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. ...

1 Dialogue Logic In Dialogue Logic the validity of some given formula F is examined in two person, perfect information games. There are two players moving alternatively, both having complete information of the current situation of the game. The player who claims being able to justify F is called the proponent, his adversary the opponent. The initial state, the dialogue setting, is determined by...

The status and the treatment of detainees in the ‘war on terror’ is one of the major contentious topics in current transatlantic relations. This article aims to explain the reasons for transatlantic disunity on this issue as well as to assess its impact on the stability and the persistence of the transatlantic security community. I argue that divergent strategic cultures are the main source of ...

Conversational recommender systems (CRSs) approach user preference acquisition from a conversational point of view, where preferences are captured and put to use in the course of on-going natural language dialogue. The approach is motivated by its aim to make interaction efficient and natural, to acquire preferences from the user in a context when she is motivated to give them, as well as to fa...

We take a simple form of non-adversarial persuasion dialogue in which one participant (the persuader) aims to convince the other (the responder) to accept the topic of the dialogue by asserting sets of beliefs. The responder replies honestly to indicate whether it finds the topic to be acceptable (we make no prescription as to what formalism and semantics must be used for this, only assuming so...

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 evaluating the result with real users. We use Reinforcement Learning (RL) to learn multimodal dialogue strategies by interaction with a simulated environment which is “bootstrapped” from small amounts of Wizard-of-Oz (WOZ) data....

Speech enabled interfaces are nowadays becoming ubiquitous. The most advanced ones rely on probabilistic pattern matching systems and especially on automatic speech recognition systems. Because of their statistical nature, performances of such systems never reach one hundred percent of correct recognition results. Performances are linked to environmental noise and to intraand inter-speaker vari...