Entity recommendation, providing search users with an improved experience by assisting them in finding related entities for a given query, has become an indispensable feature of today's Web search engine. Existing studies typically only consider the query issued at the current time step while ignoring the in-session preceding queries. Thus, they typically fail to handle the ambiguous queries such as "apple" because the model could not understand which apple (company or fruit) is talked about. In this work, we believe that the in-session contexts convey valuable evidences that could facilitate the semantic modeling of queries, and take that into consideration for entity recommendation. Furthermore, in order to better model the semantics of queries, we learn the model in a multi-task learning setting where the query representation is shared across entity recommendation and context-aware ranking. We evaluate our approach using large-scale, real-world search logs of a widely used commercial Web search engine. The experimental results show that incorporating context information significantly improves entity recommendation, and learning the model in a multi-task learning setting could bring further improvements.

Entity highlight refers to a short, concise, and characteristic description for an entity, which can be applied to various applications. In this article, we study the problem of automatically generating entity highlights from the descriptive sentences of entities. Specifically, we develop two computational approaches, one is inspired by the statistical machine translation (SMT) and another is a sequence-to-sequence learning (Seq2Seq) approach, which has been successfully applied in neural machine translation and neural summarization. In the Seq2Seq approach, we use attention mechanism, copy mechanism, and coverage mechanism. To generate entity-specific highlights, we also incorporate entity name into the Seq2Seq model to guide the decoding process. We automatically collect large-scale instances as training data without any manual annotation, and ask annotators to create a test set. We compare with several strong baseline methods, and evaluate the approaches with both automatic evaluation and manual evaluation. Experimental results show that the entity enhanced Seq2Seq model with attention, copy, and coverage mechanisms significantly outperforms all other approaches in terms of multiple evaluation metrics.1