Last week our project proposal to the Swedish Research Council VR on Collaborative Robot-Assisted Language Learning (CORALL) was awarded a four year funding (2017–2020), and since it targets a specific use of technologies for collaborative learning, I feel that a project description and a ONL162-tainted reflection on the upcoming project is fitting for the blogpost on the topic of Learning in communities – networked collaborative learning.
Collaborative Robot-Assisted Language Learning
The societal purpose of CORALL is to contribute to more effective education of Swedish for Immigrants by combining pedagogy of collaborative learning with technology for computer-assisted language learning and social robotics.
The scientific aims of the CORALL project are to:
- introduce robot and computer-animated tutors in spoken communication training
- explore collaborative task-based learning with two learners and a robot tutor
- adapt practice and feedback interaction to the individual’s abilities using learner modelling, automatic assessment and motivation tracking
The collaborative learning set-up, shown in the picture above, focuses on functional communication, practised using engaging and relevant tasks. The practice targets robot-assisted human-human communication, in which the robot tutor can initiate, support and monitor the interaction between the two learners, and learners can support each other in their learning, on both communicative and linguistics aspects. Individual pre- and post-sessions allow the learners to focus on their specific needs together with a computer-animated tutor.
The technological part
The Furhat robotic head consists of a 3D-printed mask on which a computer-animated face is back-projected. This allows for natural face gestures, and most importantly for L2 learning, appropriate lip movements. Thanks to a motor in the neck, Furhat can rotate the head to face the interlocutor, and tilt it to face the task interaction board, on which collaborative tasks are presented. Speech technology components (automatic speech recognition and text-to-speech synthesis and a spoken dialogue system framework) enables Furhat to talk with the learners and a Kinect 3D camera and computer vision software allows the robot to see them, their interaction and their reactions to the interaction.
The pedagogical part
The pedagogical aspects of the research project consist of
- designing relevant, engaging collaborative tasks, and accompanying supportive curriculum of vocabulary and phrases.
- defining tutor behaviour and feedback strategies, to determine how the tutor should act to support the learners’ interaction, and when and how feedback on linguistic errors should be provided.
- modelling the learners’ linguistic level, in order to find a suitable peer and task for the collaborative learning session.
- modelling and tracking the learners’ motivation state, using speech recognition of the learners’ verbal and non-verbal acoustic output as well as computer vision analysis of face expressions, head and body posture etc, in order to be able to adapt the practice to the learners’ feelings about the practice.
- evaluating the pedagogical effectiveness of the training.
Reflections on CORALL from the perspective of ONL162
Based on our PBL groups’ summary of the topic, I see the following points that we should consider in the project:
- be engaging (i.e., not only in terms of linguistic training, but also regarding the topic itself).
- be truly collaborative (i.e., they, must be, or are better solved in group).
- foster the bond between the learners.
- be clear for the learners (in terms of learning objectives: both what the goal of the task is and which linguistic skills that are practiced).
- be chosen to reflect a set of predefined skills that are considered important to master.
- promote social and negotiation skills as well as pure linguistic skills.
- balance between guiding the learners towards task solution and letting them interact autonomously.
- monitor the learners closely (in terms of linguistic problems requiring assistance and motivational state requiring task adaptation or tutor intervention).
- have a clear instructional strategy.
- act as (active or passive, as appropriate) tutor, not co-learner.
- try to promote learners to contribute with their own competencies (peer feedback and support on linguistic aspects as well as collaboration on the task).
Relevant references used in the proposal
- Butler, D.L., & Winne, P.H. (1995). Feedback and self-regulated learning: a theoretical synthesis. Review of Educational Research, 65(3), 254-281.
- Engwall, O. & Bälter. O. (2007). Pronunciation feedback from real and virtual language teachers. Computer Assisted Language Learning 20.3 (2007): 235-262.
- Forbes-Riley, K., Litman, D. (2007). Analyzing dependencies between student certainness states and tutor responses in a spoken dialogue corpus, in: Dybkjaer, L., Minker, W. (eds.) Recent Trends in Discourse and Dialogue, Springer, Dordrecht.
- Goda, Y. & Yamada, M. (2012). Application of CoI to Design CSCL for EFL Online Asynchronous Discussion. Akyol, Z. & Garrison, R. (eds). Educational Communities of Inquiry: Theoretical Framework, Research and Practice, IGI Global.
- Han, J. (2012). Emerging Technologies, Robot Assisted Language Learning. Language Learning and Technology 16(3), 1–9.
- Hautopp, H. & Hanghøj, T. (2014), Game Based Language Learning for Bilingual Adults. Proceedings of the 8th European Conference on Game-Based Learning, pp. 191-198.
- Van Merriënboer, J.J.G., & Kirschner, P.A. (2007). Ten steps to complex learning: A systematic approach to four-component instructional design. London: Lawrence Erlbaum
- Åhlund, A., & Aronsson, K. (2015). Stylizations and alignments in a L2 classroom: Multiparty work in forming a community of practice. Language & Communication, 43, 11-26.
Would you like to help us get started?
As a second language learner (in particular if you are or have been learning Swedish), what authentic tasks do you feel would be (or would have been, if you are thinking about your own past experiences) relevant to practise the second language on?
Please fill in the one-question form on https://goo.gl/forms/ZukVgaTzgI9Cb0Sv2
The tasks should be suitable for beginner to intermediate level of learning Swedish, but feel free to suggest whatever comes to mind.