ACM IUI conference serves as a premier platform where experts from artificial intelligence and human-computer interaction converge to discuss advancements at their intersection. The conference is renowned for its rigorous selection process and is classified as an A-rank conference by the International Conference Ranking Exercise (ICORE), placing it among the top 15% of 784 evaluated venues.

About the award-winning paper "Text-to-Image Generation for Vocabulary Learning Using the Keyword Method"

The ‘keyword method’ is an effective technique for learning vocabulary of a foreign language. It involves creating a memorable visual link between what a word means and what its pronunciation in a foreign language sounds like in the learner’s native language. However, these memorable visual links remain implicit in the people’s mind and are not easy to remember for a large number of words. To enhance the memorisation and recall of the vocabulary, researchers developed an application that combines the keyword method with text-to-image generators to externalise the memorable visual links into visuals. These visuals represent additional stimuli during the memorisation process. To explore the effectiveness of this approach researchers first run a pilot study to investigate how difficult it is to externalise the descriptions of mental visualisations of memorable links, by asking participants to write them down. These descriptions were used as prompts for text-to-image generator (DALL-E 2) to convert them into images and participants were asked to select their favourites. Next, different text-to-image generators (DALL-E 2, Midjourney, Stable and Latent Diffusion) were compared to evaluate the perceived quality of the generated images by each.

Despite heterogeneous results, participants mostly preferred images generated by DALL-E 2, which was used also for the final study. In this study, researchers investigated whether providing such images enhances the retention of vocabulary being learned, compared to the keyword method alone. The results indicate that people did not encounter difficulties describing their visualisations of memorable links and that providing corresponding images significantly increases memory retention.

The paper was co-authored by 12 researchers, including Assist. Prof. Nuwan T. Attygalle, Assoc. Prof. Matjaž Kljun, Assoc. Prof. Klen Čopič Pucihar and Asist. Prof. Maheshya Weerasinghe from UP FAMNIT. The research was conducted in collaboration with researchers from the University of Luxembourg, CSIRO Data61 (data and digital specialist arm of Australia's national science agency), Coburg University of Applied Sciences, the University of St Andrews and the Nara Institute of Science and Technology.