Improving personalised query reformulation with embeddings

As a mechanism to guide users towards a better representation of their information needs, the query reformulation method generates new queries based on users’ historical queries. To preserve the original search intent, query reformulations should be context-aware and should attempt to meet users’ personal information needs. The mainstream method aims to generate candidate queries first, according to their past frequencies, and then score (re-rank) these candidates based on the semantic consistency of terms, dependency among latent semantic topics and user preferences. We exploit embeddings (i.e. term, user and topic embeddings) to use contextual information and individual preferences more effectively to improve personalised query reformulation. Our work involves two major tasks. In the first task, candidate queries are generated from an original query by substituting or adding one term, and the contextual similarities between the terms are calculated based on the term embeddings and augmented with user personalisation. In the second task, the candidate queries generated in the first task are evaluated and scored (re-ranked) according to the consistency of the semantic meaning of the candidate query and the user preferences based on a graphical model with the term, user and topic embeddings. Experiments show that our proposed model yields significant improvements compared with the current state-of-the-art methods.