Joel Mackenzie

Personal Website Google Scholar GitHub

Lecturer, UQ.

My research focuses on efficient and effective representations for large-scale search engines, including indexing, compression, and retrieval. I am also interested in understanding how to measure improvements in the end-to-end search pipeline, including system-oriented effectiveness measurements and user behaviour analysis. I have a broad interest in empirical experimentation, operating systems, data structures, and algorithms. Please see my personal site for more details.

Publications

• Joel Mackenzie and Shengyao Zhuang and Guido Zuccon. 2023. Exploring the Representation Power of SPLADE Models. In The Proceedings of the 2023 ACM SIGIR on International Conference on Theory of Information Retrieval (ICTIR 2023).