Data-Driven Evaluation Metrics for Heterogeneous Search Engine Result Pages

Leif A. Azzopardi, Ryen W. White, Paul Thomas, Nick Craswell · 2020

Evaluation metrics for search typically assume items are homoge- neous. However, in the context of web search, this assumption does not hold. Modern search engine result pages (SERPs) are composed of a variety of item types (e.g., news, web, entity, etc.), and their influence on browsing behavior is largely unknown.

Read the paper · More papers on PaperTik