We showcase TODAY, a semanticsenhanced task-oriented dialogue translation system, whose novelties are: (i) taskoriented named entity (NE) definition and a hybrid strategy for NE recognition and translation; and (ii) a novel grounded semantic method for dialogue understanding and task-order management. TODAY is a case-study demo which can efficiently and accurately assist customers and agents in...

We introduce a concept-to-speech (CTS) system that generates prosodic structure compositionally, in a spoken dialogue agent architecture . Representations from the semantic interpretation, task modeling, and dialogue strategy selection components drive the computation of accentuation, pitch accent type selection, and choice of melodic contour, respectively. These principled couplings of dialogu...

This system demonstration paper presents IRIS (Informal Response Interactive System), a chat-oriented dialogue system based on the vector space model framework. The system belongs to the class of examplebased dialogue systems and builds its chat capabilities on a dual search strategy over a large collection of dialogue samples. Additional strategies allowing for system adaptation and learning i...

We introduce multidimensional feature structures as a generalization of standard slot/filler representations commonly employed in spoken language dialogue systems. Nodes in multidimensional feature structures contain an dimensional vector of values instead of one single filler element. The additional elements serve to represent, among other information, confidence measures of speech recognizers...

In this paper, we present a data-driven approach for detecting instances of miscommunication in dialogue system interactions. A range of generic features that are both automatically extractable and manually annotated were used to train two models for online detection and one for offline analysis. Online detection could be used to raise the error awareness of the system, whereas offline detectio...

We propose a software architecture designed to ease the implementation of dialogue systems. The Modular Architecture for Conversational Agents (MACA) uses a plug-n-play style that allows quick prototyping, thereby facilitating the development of new techniques and the reproduction of previous work. The architecture separates the domain of the conversation from the agent’s dialogue strategy, and...

Dialogue systems that process user contributions only in chunks bounded by silence miss opportunities for producing helpful signals, such as backchannel utterances concurrent with the ongoing utterance— to the detriment of interaction quality. We survey in some detail what we call ‘subutterance’ phenomena, which such an approach misses, and then discuss two approaches to overcoming this limitat...

We advocate an objective evaluation methodology for the automated evaluation of spoken dialogue systems that eliminates manual interaction and reduces annotation errors and personal bias. The evaluation is performed by observing interactions between the system and a simulated user. We argue that user simulation is an inexpensive and feasible method for optimizing a dialogue system in the lab. U...