Personalized Language Model for Query Auto-Completion
This work addresses the need for more accurate and user-specific query suggestions in search engines, though it is incremental as it builds on existing language model approaches.
The paper tackled the problem of generating personalized query completions in search engines by using an adaptable recurrent neural network language model with online updating, resulting in significantly better predictions than a baseline without user information.
Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types. Recently, the use of a recurrent neural network language model was suggested as a method of generating query completions. We show how an adaptable language model can be used to generate personalized completions and how the model can use online updating to make predictions for users not seen during training. The personalized predictions are significantly better than a baseline that uses no user information.