A dialogue system for answering user questions in natural speech presents one of the main achievements of contemporary interaction-based AI technology. Modern dialogue frameworks function as middleware between the interface component and the backend where the answers to the user questions are stored in heterogeneous formats. We implemented an interface to linked data sources as part of a comple...

  This study attempted to investigate whether there was any significant difference between the speaking achievement of learners who were trained by means of audiotaped dialogue journal, dialogue journal writing, or traditional free speech. The participants, 45 male and female students aged between 21 and 32, were selected by random sampling from among free speech classes in an English teaching...

It is undoubtedly true that one prominent component of effective human tutoring is collaborative dialogue between student and tutor [7, 12]. Nevertheless, many important questions remain to be answered about which features of human tutorial dialogue make it effective and how the most effective human tutoring strategies can be implemented in a tutorial dialogue system. In this paper we present a...

The paper argues for the importance of utterances (as opposed to \sen-tences in context") as basic units in dialogue. The main case study is clar-iication: a characterization is provided within KOS, a recently developed synthesis of situation semantics and dialogue games, of the clariications that can follow up on an utterance. This involves outlining: (a) a theory of understanding for dialogue...

Much previous work on generation has focused on the general problem of producing lexical strings from abstract semantic representations. We consider generation in the context of a particular task, creating full sentential paraphrases of fragments in dialogue. When the syntactic, semantic and phonological information provided by a dialogue fragment resolution system is made accessible to a gener...

The development of spoken dialogue systems is often limited by the performance of their speech recognition component. The impact of speech recognition errors on dialogue systems is often studied at the global level of task completion. In this paper, we carry an empirical study on the consequences of speech recognition errors on a fully-implemented dialogue prototype, based on a speech acts form...

This overview article reviews the structure of a fully statistical spoken dialogue system (SDS), using as illustration, various systems and components built at Cambridge over the last few years. Most of the components in an SDS are essentially classifiers which can be trained using supervised learning. However, the dialogue management component must track the state of the dialogue and optimise ...

This paper reports on user evaluation for a spoken dialogue system and the subsequent redesign of the dialogue strategy. An automatic telephone directory system developed at Philips Research, PADIS, was evaluated using both objective metrics and subjective evaluation techniques. Duration and the occurrence of misunderstanding leading tòdead-ends', were found to be the key factors that kept user...

Adjacency pair recognition, a necessary component of discussion thread reconstruction, is the task of recognizing reply-to relations between pairs of discussion turns. Previously, dialogue act classification and metadata-based features have been shown useful in adjacency pair recognition. However, for certain forums such as Wikipedia discussions, metadata is not available, and existing dialogue...