Attention-based Hierarchical Neural Query Suggestion

TL;DR

This paper introduces AHNQS, a hierarchical neural network model with attention for query suggestion, capturing user preferences from search history to improve suggestion accuracy.

Contribution

The paper presents a novel hierarchical neural query suggestion model that incorporates attention to better model user preferences from search history.

Findings

AHNQS outperforms state-of-the-art RNN-based methods in MRR@10 and Recall@10.

Significant improvements are observed especially for short search sessions.

The model effectively captures user preferences through attention mechanisms.

Abstract

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.