Context Attentive Document Ranking and Query Suggestion
This work addresses search efficiency for users by incrementally advancing context-aware ranking and query suggestion methods.
The paper tackled the problem of improving retrieval performance by modeling users' search context, achieving enhanced results through a two-level hierarchical recurrent neural network with attention mechanisms.
We present a context-aware neural ranking model to exploit users' on-task search activities and enhance retrieval performance. In particular, a two-level hierarchical recurrent neural network is introduced to learn search context representation of individual queries, search tasks, and corresponding dependency structure by jointly optimizing two companion retrieval tasks: document ranking and query suggestion. To identify the variable dependency structure between search context and users' ongoing search activities, attention at both levels of recurrent states are introduced. Extensive experiment comparisons against a rich set of baseline methods and an in-depth ablation analysis confirm the value of our proposed approach for modeling search context buried in search tasks.