SMALLA

Smart and Immersive Language Learning Environment

Language learning is a process that requires focus and immersion in the target language. With regards to e-learning, in which the language learner is much more autonomous in his or her language learning process, having an immersive virtual platform that enables the learners to pursue their own goals is a challenge to be reckoned with. In this scenario, it is important that the platform offers both ready-to-use instruments and adaptive resources that can recognize user-developed or user-prompted materials. In this way, the learners can focus on their own interests.

Distance learning is a flexible solution for coping with the extreme diversity of language learners interested in vocational training. E-learning solutions enable people, at any stage of their life, to take part in stimulating learning experiences. And it is clear that the adoption of these learning tools increases. Many free e-learning platforms (of various quality and coverage) have been released in the last few years and they tend to recruit more and more users, even if they sometimes have strong limitations. On the professional market, the same observation can be made: for the sole Walloon Region, more than 400.000 peoples enrolled in the Wallangues projects run by Altissia for the RW government.

As language learners get used to the e-learning paradigm, as they raise the expectations about the e-learning environment (e.g. customization, adaptiveness of profile, constant feedback, and rapid results). Regarding learner engagement, the learning environment must include motivational aspects (e.g. gamification) and provide, when possible, live coaching (blended approach mixing e-learning and natural interaction in online classrooms). All this calls for the integration of Artificial Intelligence tools and advanced language technologies. In short, the learning platform needs to become “smarter” to understand the learner needs and interests.

This project inserts itself in this scenario via a partnership between the Catholic University of Louvain, specifically the Centre de traitement automatique du langage (CENTAL), and Altissia, an enterprise dedicated to e-learning that handles Erasmus+ Online Linguistic Support (http://erasmusplusols.eu/). This partnership is not new, and there are a few other projects that were already developed. Here are some of the codeveloped projects: The CENTAL has developed tools for text normalisation and spell checking programs in the framework of a RW First Spin Off project. The project leads to the development of technologies on which is based a training platform that has been licensed to Altissia. The new platform will be commercially available in October 2016. The CENTAL is also doing research on open answer language evaluation. The aim is to automatically assess student’s writing in language tests. Altissia and CENTAL are therefore experienced in collaborative research and have successfully collaborated in the past to the valorization of projects. Together they have just launched a joint research project dedicated to the design of a “Smart and Immersive Language Learning Environment” (SMILLE, supported by a Beware Grant). The idea behind this first Beware project is to make use of computational tools and linguistic knowledge for developing an environment that will have impact on the e-learning process. The focus is on the “immersion” of the learner in the target language. Immersion is seen as a means for offering the learner the possibility to engage in his own interest while studying a new language. With this aim in view, the platform will provide to the learner access to text that follows his interests and language skills and even the possibility to add new texts to the learning path. The system we describe in this project will create a user profile, and use it to retrieve recommended texts according to user profile and interests.

This is more critical when we consider that many language learners have professional interests, in other words, they are interested in specific domain content. SMILLE is an ambitious project that will deeply dig into the field of Computational Linguistics (according to Jurafsky and Martin [1], the goal of computational linguistics is “to get computers to perform useful tasks involving human language, tasks like enabling human-machine communication, improving human-human communication, or simply doing useful processing of text or speech”). The SMILLE project plans to design the ‘immersive’ approach on the basis of two computational ‘assistants’: a ‘reading assistant’ (a set of tools that help the user to read new texts related to his/her interests) and a ‘teaching assistant’ (a set of tools integrated with the learning platform, that can use the feedback information provided by the ‘reading assistant’ in order to create new learning exercises along the learning path of the Altissia platform). The goal of the SMILLE project is to make a breakthrough in the domain of e-learning by designing the foundations of a fully fledged “e-Immersion”.

However, specific domain content usually contains text not accessible for beginner and intermediate language learners. To select pieces of text that fits with user profile, we will need to figure out text features able to estimate learner skills of grammar, vocabulary, key communicative phrases, and reading comprehension. Besides the learners’ immersion, which helps them to keep engaged in language learning process, another project contribution is to help language teacher to find text for students, since text selection is a time expensive task for teacher. So, this project will support SMILLE project and language teachers. And, beyond that, it will allow learners to improve their language skills at the same time as they read about their own interests.

The fruits of this project are focused both on the enterprise and on the academic side of the partnership. The resources that will be developed require scientific research of the languages involved (primarily English, but with a methodology that will be adaptable to other languages, such as Portuguese and the other languages that are of interest for Altissia) and will be developed on the online e-learning platform that is managed by Altissia.

Financement

• Région wallonne, DGO6, BEWARE

Parrainage

• Altissia

Dates

• 2017-2019

Chercheur