Award-winning computer science researcher Doctor Danushka Bollegala has partnered with global recipe sharing platform Cookpad Ltd on a range of projects looking at natural language processing (NLP) and machine learning.
Having studied for 13 years in Japan, the senior lecturer at the University of Liverpool has been named as Senior Fellow at Cookpad, where he is working with the Bristol-based team on an analysis of the language associated with the many thousands of recipes and ingredients on the site and their complexity.
Well known within computer engineering circles, Dr Bollegala has been researching NLP, machine learning and data mining for more than 10 years.
During this time, he has published more than 100 peer reviewed papers in top academic journals and written three books.
He started working with Cookpad late last year after meeting their chief technology officer Miles Woodroffe and discussing the work the company was doing on machine learning and NLP in the context of food and recipe terms.
Dr Bollegala is now working with the Cookpad team on a number of projects, with the primary focus on name recognition for ingredients. The aim is to build a system that can recognise and analyse key terms in the recipes across Cookpad’s platforms to enable users to search all the recipes featuring certain food types.
Dr Bollegala said: “All this work is a practical application of my academic learning and offers opportunities to carry out further research in a real-world setting.
“We are developing the NLP capabilities to enable people to search more easily for recipes with certain ingredients or find out what can replace ingredients they may not have.
“At the moment it is very difficult to automatically evaluate the difficulty of the recipe so we’re building machine learning model that can grade the difficulty of a recipe.”
Cookpad is one of the most popular cooking platforms in the world, currently operating in 22 languages across 70 countries worldwide from its global headquarters in Bristol.