Bøger i Foundations and Trends (R) in Information Retrieval serien

Reviews the published literature on search result diversification. In particular, the book discusses the motivations for diversifying the search results for an ambiguous query and provides a formal definition of the search result diversification problem.

Focuses predominantly on the problems and solutions proposed in traditional areas while also looking briefly at the emerging areas. To facilitate future research, a discussion of available resources, a list of public benchmark datasets and a discussion on future research directions are provided in the concluding sections.

The key to the success of the deep learning approach is its strong ability in learning of representations and generalization of matching patterns from data. This survey gives a systematic and comprehensive introduction to the deep matching models for search and recommendation.