This study investigates EFL learners’ dialogues in synchronous task-based computer-mediated communication (CMC). The focus is on whether learners engage each other in text-based dialogues regarding the language use in pursuit of the task goal in the CMC context and how their mutual engagement impacts their language learning. Sixteen Chinese tertiary-level learners voluntarily participated in th...

A natural language collaborative consultation system must take user preferences into account. A model of user preferences allows a system to appropriately evaluate alternatives using criteria of importance to the user. In addition, decision research suggests that an accurate model of user preferences could enable the system to improve a user's decision-making by ensuring that all important alte...

A natural language collaborative consultation system must take user preferences into account. This paper presents two strategies: one for dynamically recognizing user preferences during the course of a collaborative planning dialogue and another for exploiting the model of user preferences to detect suboptimal solutions and suggest better alternatives. By modeling and utilizing user preferences...

Research in collaborative learning has supported the hypothesis that dialogue between peers and between peers and teachers facilitates learning by the peer participants in the dialogue. Examples of these dialogues show dozens of turns (individual utterances by participants) in a single learning session. In contrast, measurements of interaction from computer-supported collaborative learning envi...

Interpretive Collaborative Review (ICR) is a process designed to assemble electronically accessible research papers and other forms of information into collaboratively interpreted guides to information artefacts relevant to particular problems. The purpose of ICR is to enable collective understanding of a selected problem area that can be developed and represented by evaluating (reviewing) sele...

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...

In the CommRob project we are investigating Robot Assisted Shopping. We are considering the effects on usability when allowing for mixed-initiative dialogue. It is noted that when adding a robotic assistant to a scenario that was previously involving only one agent, two new tasks are created: collaborative interaction, and learning an interface. Evaluation of mixed-initiative dialogue becomes c...

To be effective, an agent that collaborates with humans needs to be able to learn new tasks from humans they work with. This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue. To accomplish this, the system integrates a range of AI technologies: deep natural language understanding, knowl...

This paper introduces a new learning technology for classroom learning. The system and practice is called “Livenotes” and is motivated by the empirical success of peer learning methods, and by theoretical considerations of distributed dialogue among student peers as a facilitator of learning. The technical part of Livenotes is a shared whiteboard running on wireless handheld computers. We descr...