Found in Translation is an interactive, immersive installation for the exhibition Translations at 21_21 Design Sight in Tokyo. Using their own spoken sentences, visitors viscerally experience the process of machine translation. Visualizations show how the machine learning model clusters words from different languages by semantic similarity, and translations are presented typographically and auditorily across 24 languages.
The spatial environment consists of 24 screen panels and 24 audio speakers distributed across the room. The panels are organized and color-coded by language family, and each panel represents one language in text, diagrams and sound. In the center of the room is a microphone on a pedestal. When a visitor approaches the microphone the center panel shows a question as a prompt. Once an answer is spoken into the microphone a visualization shows the multi-lingual machine learning model that is used for translations. Word by word and sentence by sentence it becomes apparent which words from which languages are clustered together.
The visualizations travel across the entire room, showing a spatialized version of a small multiple diagram across the room. Each diagram in turn animates into the text version of the translation, as the translated text is spoken in voice.
The back panel provides background information on the technology behind the installation, explaining multi-lingual machine learning models, transfer learning and other findings by language machine learning researchers.
This is a TheGreenEyl project created in collaboration with Google Creative Lab and Dominick Chen.