Following the tradition of in-house tech and practical talks here at Textkernel, we've decided to open our doors and make those talks public. Whether you're interested in semantic recruitment technologies, machine learning, NLP, modern software engineering technologies and practices; or just want to learn more about Textkernel, you're more than welcome to one of our talks.
Join us for an interesting state-of-the-art Tech Talk followed by a discussion, pizza and beers!
Learning to rank provides methods for optimizing ranking systems, enabling effective search and recommendation systems. Traditionally, these methods relied on annotated datasets i.e. relevance labels for query-document pairs provided by human judges. Over the years, the limitations of such datasets have become apparent, most importantly: they are expensive to create and do not necessarily reflect user preferences. Recently attention has mostly shifted to methods that learn from user interactions, as they more closely indicate user preferences. However, user interactions contain large amounts of noise and bias, learning while naively ignoring these biases can lead to detrimental results. Consequently, the current focus is on unbiased methods that can reliably learn from user interactions. In this talk I will contrast the two main approaches to unbiased learning to rank: counterfactual learning and online learning, and discuss the most recent methods from the field.
Harrie Oosterhuis (https://staff.fnwi.uva.nl/h.r.oosterhuis) is a 3rd year PhD student under supervision of Prof. dr. Maarten de Rijke at the University of Amsterdam. His main topic is learning to rank from user behaviour and he has publications at major IR conferences including CIKM, SIGIR, ECIR and WSDM. In addition he has completed multiple internships at Google Research & Brain in California, and worked as a visiting student at RMIT university in Melbourne during his PhD.