Attention-based Hierarchical Neural Query Suggestion
This addresses query refinement for search engine users, offering incremental improvements over existing methods.
The paper tackles the problem of generating query suggestions for search engines by modeling short- and long-term user search history with a hierarchical neural network and attention mechanism, achieving improvements of up to 21.86% in MRR@10 and 22.99% in Recall@10 over state-of-the-art baselines on the AOL dataset.
Query suggestions help users of a search engine to refine their queries. Previous work on query suggestion has mainly focused on incorporating directly observable features such as query co-occurrence and semantic similarity. The structure of such features is often set manually, as a result of which hidden dependencies between queries and users may be ignored. We propose an AHNQS model that combines a hierarchical structure with a session-level neural network and a user-level neural network to model the short- and long-term search history of a user. An attention mechanism is used to capture user preferences. We quantify the improvements of AHNQS over state-of-the-art RNN-based query suggestion baselines on the AOL query log dataset, with improvements of up to 21.86% and 22.99% in terms of MRR@10 and Recall@10, respectively, over the state-of-the-art; improvements are especially large for short sessions.