This document discusses evaluation methods for information retrieval systems. It begins by outlining different types of evaluation, including retrieval effectiveness, efficiency, and user-based evaluation. It then focuses on retrieval effectiveness, describing commonly used measures like precision, recall, and discounted cumulative gain. It discusses how these measures are calculated and their limitations. The document also introduces other evaluation metrics like R-precision, average precision, and normalized discounted cumulative gain that provide single value assessments of system performance.