Predicting Relevance based on Assessor Disagreement: Analysis and Practical Applications for Search Evaluation
This work addresses the challenge of making search evaluation more robust and generalizable for information retrieval researchers and practitioners, though it is incremental as it builds on existing evaluation frameworks.
The paper tackles the problem of search engine evaluation by addressing assessor disagreement on relevance judgments, proposing the Predicted Relevance Model (PRM) to predict relevance for random users based on observed assessments and average disagreement, which transforms binary metrics into graded measures and provides principled gains for metrics like nDCG.
Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the results for general (e.g., future, unknown) users. In practice however, most evaluation scenarios only allow us to conclusively determine the relevance towards the particular assessor that provided the judgments. A factor that cannot be ignored when extending conclusions made from assessors towards users, is the possible disagreement on relevance, assuming that a single gold truth label does not exist. This paper presents and analyzes the Predicted Relevance Model (PRM), which allows predicting a particular result's relevance for a random user, based on an observed assessment and knowledge on the average disagreement between assessors. With the PRM, existing evaluation metrics designed to measure binary assessor relevance, can be transformed into more robust and effectively graded measures that evaluate relevance towards a random user. It also leads to a principled way of quantifying multiple graded or categorical relevance levels for use as gains in established graded relevance measures, such as normalized discounted cumulative gain (nDCG), which nowadays often use heuristic and data-independent gain values. Given a set of test topics with graded relevance judgments, the PRM allows evaluating systems on different scenarios, such as their capability of retrieving top results, or how well they are able to filter out non-relevant ones. Its use in actual evaluation scenarios is illustrated on several information retrieval test collections.