Entity Recommendation and Understanding


Hao Ma, Microsoft Research


Recent years have witnessed rapidly increasing interests on the research field of semantic search. Knowledge base powered entity search and recommendation experience has been widely adopted by major search engine companies. Although many work has been introduced in the field of traditional recommender systems or information retrieval, entity recommendation and search techniques differ significantly from them due to the introduction of knowledge base. The heterogeneity, semantic richness and large-scale nature of knowledge base make traditional approaches less effective. In this talk, Dr. Ma will provide a brief introduction on how entity recommendation works and how various entity understanding techniques could further improve entity recommendation and search experience. More specifically, Dr. Ma will first demonstrate various entity recommendation and search applications he and his colleagues designed and productionized in Bing, including entity recommendation, natural language interpretation of recommendation,  attribute ranking, carousel ranking, entity exploration, factoid answers, conversational question and answering, etc. Then Dr. Ma will give a deep dive on some of the recommendation algorithms that are related to entity recommendation, including basic non-personalized recommendation algorithms as well as recommendation models that tailor related entities to an individual search user's unique taste and preference.  This talk will conclude by summarizing a whole area of exciting and dynamic research that is worthy of more detailed investigation for many years to come.