We demonstrate an English/Chinese bilingual weather information system that is configured as both a conversational partner and a tutor for foreign language (L2) students to practice conversational skills.

We present Dialog Moves Markup Language (DMML): an extensible markup language (XML) representation of modality independent communicative acts of automated conversational agents. In our architecture, DMML is the interface to and from conversational dialog managers for user interactions through any channel or modality. The use of a common XML interface language across different channels promotes ...

Recent advances in Artificial Intelligence (AI) and machine learning have paved the way for increasing adoption of chatbots language learning. Research published to date has mostly focused on chatbot accuracy chatbot–human communication from students’ or in-service teachers’ perspectives. This study aims examine knowledge, level satisfaction perceptions concerning integration conversational AI ...

In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations. Different architectures are explored for integrating participant role and context information into a Long Short-term Memory (LSTM) language model. The conversational model can function as a language model or a language generation model. Experiments on the Ubuntu Dial...

Preference dialogues display several interesting characteristics that have implications on how to design human-like dialogue strategies in conversational recommender systems. Using human-human preference dialogues as an empirical base, this paper introduces a novel data manipulation language called PCQL that comprises explicit descriptive, comparative and superlative preference management as we...

This paper describes a data-driven methodology for the design of multilingual conversational systems. The work presented here covers the various aspects of bootstrapping and deploying multilingual systems, such as phone set definition, acoustic modeling, language modeling, and language understanding. For the initial system domain, a Directory Assistance Service has been chosen. Whereas former a...

Language modeling for conversational speech suffers from the limited amount of available adequate training data. This paper describes a new approach that performs the estimation of the language model probabilities in a continuous space, allowing by these means smooth interpolation of unobserved n-grams. This continuous space language model is used during the last decoding pass of a state-of-the...

1 Abstract We present work in progress on creating and using a novel audiovisual database that contains a diverse set of conversational expressions. The database is currently undergoing cleaning, annotation and validation to make it useful for the research community. While our main focus is on conversational expressions, we believe that the audio data is of use for the language community. We ai...