University of Washington at TREC 2020 Fairness Ranking Track
This work addresses fairness in information retrieval for academic search systems, but it is incremental as it builds on existing track participation and methods.
The paper tackled the problem of incorporating fairness in retrieval and re-ranking tasks by extracting author identity dimensions like gender and location from Semantic Scholar data, with results showing below-average performance for re-ranking but above-average for retrieval.
InfoSeeking Lab's FATE (Fairness Accountability Transparency Ethics) group at University of Washington participated in 2020 TREC Fairness Ranking Track. This report describes that track, assigned data and tasks, our group definitions, and our results. Our approach to bringing fairness in retrieval and re-ranking tasks with Semantic Scholar data was to extract various dimensions of author identity. These dimensions included gender and location. We developed modules for these extractions in a way that allowed us to plug them in for either of the tasks as needed. After trying different combinations of relative weights assigned to relevance, gender, and location information, we chose five runs for retrieval and five runs for re-ranking tasks. The results showed that our runs performed below par for re-ranking task, but above average for retrieval.