This paper reports on the efforts of twelve national teams in building the International Comparable Corpus (ICC; https://korpus.cz/icc) that will contain highly comparable datasets of spoken, written and electronic registers. The languages currently covered are Czech, Finnish, French, German, Irish, Italian, Norwegian, Polish, Slovak, Swedish and, more recently, Chinese, as well as English, which is considered to be the pivot language. The goal of the project is to provide much-needed data for contrastive corpus-based linguistics. The ICC corpus is committed to the idea of re-using existing multilingual resources as much as possible and the design is modelled, with various adjustments, on the International Corpus of English (ICE). As such, ICC will contain approximately the same balance of forty percent of written language and 60 percent of spoken language distributed across 27 different text types and contexts. A number of issues encountered by the project teams are discussed, ranging from copyright and data sustainability to technical advances in data distribution.
This paper explores the application of AI image generation in Computer-Assisted Language Learning (CALL) for Less Commonly Taught Languages (LCTLs). It delves into the potential of text to image generation models in creating context specific visual aids to enhance comprehension and engagement among learners. The integration of AI generated images in a language learning game, Cipher, is discussed, showcasing the benefits and challenges encountered. Learner feedback indicates positive inclinations towards the AI generated images, but also highlights the need for meticulous selection to address biases and stereotypes. Overall, this approach shows promise in creating culturally relevant CALL resources and improving language learning experiences for learners of LCTLs.
1 January 2006 in Lecture Notes in Computer Science
Traditional language learning methods often fall short in engaging learners, especially in the context of indigenous languages like Irish. In this study we show how the language learning game Cipher VR combines digital game-based language learning with Virtual Reality (VR) to reconnect learners with indigenous languages, using the Irish language as a case study. Initially designed for English, Cipher has undergone several iterations to adapt to the Irish context, and is now completing its metamorphosis into a VR platform aimed at meeting the needs of less-resourced and endangered languages. This paper explores Cipher VR's development, emphasising the learner-centric design that merges educational aims, engaging gameplay and a culturally grounded approach to create an immersive and motivating learning experience.
Game Based Language Learning (GBLL) is an approach to language learning in which learning happens in the process of playing a game. GBLL has several potential benefits including enhanced reading, writing, and cultural awareness. This paper provides a brief overview of Cipher – Faoi Gheasa, a GBLL app for Irish and learners’ feedback on the game. The app inverts the current Intelligent Computer Assisted Language Learning (ICALL) approach to error detection and it asks players (learners) to spot the deliberate errors (ciphers) in texts that have been changed by an evil character called Sypher. Many elements of game playing are included in the app. It has been played by over 150 primary school learners of Irish. While there is still room for improvement, the overall feedback from the students was very positive.