Natural language processing enhances predictive modelling
Algorithmically, ideas similar to those used for the next binge or the next purchase are used, but developed with educational and neuro-scientific nuances in mind so that students are given what they need, not just more of what they want. Century’s recommender systems trained on student behaviour suggest learning options tailored to every pupil. Clustering frameworks identify the guidance different student groups need, and natural language processing – powered by rich banks of qualitative content and student-teacher-input text – enhances predictive modelling.
Century’s AI product is built on a rich data store, the foundation for all great machine learning-based technologies. It uses a range of machine learning algorithms and systems that are fed on huge amounts of data diligently collected and cleaned until they are able to make decisions and recommendations by themselves for the individual student. The data banks have also expanded to the marking of students’ work, such as feedback on student-typed answers that consider both semantic and grammatical nuances in their language. Century is thus at the forefront of recommender system design, taking ever more learner behaviours into account.
- Century’s algorithms have been trained for years among thousands of students and are constantly being improved.
- Century automates the suitable tasks for machines so teachers can focus on building relationships with their students
- Century allows teachers to observe their students in ways that a machine cannot, and guide them like only a human can.
gallery
“Algorithms are among us, they are an ever-growing part of our culture, their output is based on what they are trained on and who trains them. The pavilion is at once an expression of the ideal of a culturally diverse Britain that I grew up with, tempered with our growing awareness of the part algorithms play in shaping the future of our culture.”- Es Devlin.
The idea draws directly on one of Stephen Hawking’s final projects, ‘Breakthrough Message’, a global competition that Hawking and his colleagues conceived in 2015 inviting people worldwide to consider what message we would communicate to express ourselves as a planet, should we one day encounter other advanced civilizations in space. As a result, The Poem Pavilion is a wooden sculptural structure featuring a breathtaking illuminated ‘message to space’ to which each all visitors are invited to contribute. It celebrates cultural diversity and collaboration, highlighting Britain as a meeting place of cultures and ideas.
DESCRIPTION
Visitors are invited to donate a word at the “mouthpiece” upon entering the central space, which showcases these contributions in English and Arabic, accompanied by a choral soundscape. An algorithm compiles the donated words into texts, generating a collective poem every minute.
TECHNOLOGY
The Poem Pavilion uses advanced machine learning algorithms to transform the input of visitors into collective poems. The latter can be read in illuminating displays on the façade, transforming the pavilion into the exhibit itself.
ARTIST BIO
Es Devlin is an artist and designer known for her large-scale performative sculptures and environments that fuse music, language and light. As a recipient of numerous prestigious awards worldwide, she first explored machine-generated poetry in 2016 with the Poem Portraits at the Serpentine Gallery.