Search

In the modern information society, learning is no longer just about obtaining factual knowledge, but more about general skills on how and where to apply available knowledge and obtain new knowledge in order to solve new problems. Such skills include abilities to connect and organize ideas, fill gaps in knowledge structures, evaluate evidence, argue with new information, test and modify, predict, clarify, generate questions, learn new concepts, make unexpected connections, reflect, analyze, synthesize and loop back. This work presents the Immersion framework, a digital ecosystem for adaptive smart learning environments for interactive mixed reality driven methods to foster learners' self-regulating skill development.

This paper describes the Metalogue Debate Trainee Corpus (DTC). DTC has been collected and annotated in order to facilitate thedesign of instructional and interactive models for Virtual Debate Coach application - an intelligent tutoring system used by youngparliamentarians to train their debate skills. The training is concerned with the use of appropriate multimodal rhetorical devices in orderto improve (1) the organization of arguments, (2) arguments’ content selection, and (3) argument delivery techniques. DTC containstracking data from motion and speech capturing devices and semantic annotations - dialogue acts - as defined in ISO 24617-2 anddiscourse relations as defined in ISO 24617-8. The corpus comes with a manual describing the data collection process, annotationactivities including an overview of basic concepts and their definitions including annotation schemes and guidelines on how to applythem, tools and other resources. DTC will be released in the ELRA catalogue in second half of 2018.

The paper describes experimental dialogue data collection activities, as well semantically annotated corpus creation undertaken within EU-funded METALOGUE project. The project aims to develop a dialogue system with flexible dialogue management to enable systems adaptive, reactive, interactive and proactive dialogue behaviour in setting goals, choosing appropriate strategies and monitoring numerous parallel interpretation and management processes. To achieve these goals negotiation (or more precisely multi-issue bargaining) scenario has been considered as the specific setting and application domain. The dialogue corpus forms the basis for the design of task and interaction models of participants negotiation behaviour, and subsequently for dialogue system development which would be capable to replace one of the negotiators. The METALOGUE corpus will be released to the community for research purposes.

This paper discusses the design and development of the instructional aspects of a multimodal dialogue system to train youth parliament members’ presentation and debating skills. Real-time, in-action feedback informs learners on the fly how they perform key skills and enables them to adapt instantly. About-action feedback informs learners after finishing a task how they perform key skills and enables them to monitor their progress and adapt accordingly in subsequent tasks. In- and about-action feedback together support the enhancement of the learners’ metacognitive skills, such as self-monitoring, self-regulation and self-reflection thus reflect in- and about action. We discusses the theoretical considerations of the feedback, the type of data available and different ways to analyse and combine them, the timing of feedback and, finally, provide an instructional design blueprint giving a global outline of a set of tasks with stepwise increasing complexity and the feedback proposed. We conclude with the results of the first experiment with the system focussing on non-verbal communication skills.

The main objective of METALOGUE is to produce a multimodal dialogue system that is able to implement an interactive behaviour that seems natural to users and is flexible enough to exploit the full potential of multimodal interaction. The METALOGUE system will be arranged in the context of educational use-case scenarios, i.e. for training active citizens (Youth Parliament) and call centre employees. This deliverable describes the intended real-time feedback and reflection in-action support to support the training. Real-time feedback informs learners how they perform key skills and enables them to monitor their progress and thus reflect in-action. This deliverable examines the theoretical considerations of reflection in-action, what type of data is available and should be used, the timing and type of real-time feedback and, finally, concludes with an instructional design blueprint giving a global outline of a set of tasks with stepwise increasing complexity and the feedback proposed.

The main objective of METALOGUE is to produce a multimodal dialogue system that is able to implement an interactive behaviour that seems natural to users and is flexible enough to exploit the full potential of multimodal interaction. The METALOGUE system will be arranged in the context of educational use-case scenarios, i.e. for training active citizens (Youth Parliament) and call centre employees. This deliverable describes the learner analytics and reflection support of the METALOGUE system to support the training. The provided about-action feedback informs learners how they perform key skills and enables them to monitor their progress. The aim of the about-action feedback together with the in-action feedback (see D3.1) is to support the enhancement of the learners’ metacognitive skills, such as self-monitoring, self-regulation and self-reflection. This deliverable discusses the role and scope of Learner Analytics in METALOGUE, what type of data is available and should be used, the use of Learning Dashboards and visualisations to enable the learner (and tutor) to access the outcomes of the learner analytics, a set of initial example visualisations to be used in METALOGUE, and, finally, it concludes with an instructional design blueprint giving a global outline of a set of tasks with stepwise increasing complexity and the feedback proposed.

Using the RST annotated corpus [Carlson et al., 2003], we use sim-ple statistics on the distribution of discourse markers or cue phrases as evidence of the three-way distinction of Contrast relations, Con-trast, Antithesis and Concession, recognized in standard Rhetor-ical Structure Theory (RST, Mann and Thompson 1987). We also show that however, an intuitive marker of Contrast, is not actually used statistically significantly more often in Contrast relations than in Cause-Effect relations. These results highlight the need for empirically based discourse marker identification rather than the intuitive method that is the current norm.

The work presented in this document is part of the LIRICS project and performed in Work Package 4 in close collaboration with two related initiatives. First, the area of semantic content annotation has been recognized as important by the International Organization for Standardization (ISO), which has formed the Task Domain Group TDG 3, Semantic Content, as an international expert group devoted to work in this area, within Technical Committee 37, Subcommittee 4 (Language Resource Management). In addition, an independent scientific peer group was formed within the ACL Special Interest Group on Computational Semantics (ACL/SIGSEM), the Working Group on the Representation of Multimodal Semantic Information (MMSemR). The work in WP 4 of the LIRICS project is carried out in close collaboration with this Working Group and with ISO TC 37/SC 4/TDG 3, as witnessed by joint workshops that took place in January 2005 in Tilburg (The Netherlands), in April 2006 in Marina del Rey (California), and in January 2007 in Tilburg (The Netherlands). (See also http://let.uvt.nl/research/ti/iso-tdg3 and http://let.uvt.nl/research/ti/sigsem/wg.)Following on from the discussion of methodological factors in the approach to isolating semantic descriptors for representation as outlined in the LIRICS deliverable D4.1 (Bunt and Schiffrin, 2006), this document will deal with:(Section 2) Issues in identifying commonalities in alternative approaches to the annotation and representation of various types of semantic information, and how these issues may be addressed.(Section 3) A proposal for a set of data categories in each of the four areas of consideration for semantic annotation; namely: temporal, dialogue act, reference and semantic role annotation.(Section 4) Concluding remarks on the status of the proposed data categories, their application in the constructing of multilingual test suites (described in LIRICS Deliverable D4.4), and the role of these data categories in the fields of computational linguistics and language engineering.