Query-oriented Data Augmentation for Session Search

TL;DR

This paper introduces query-oriented data augmentation for session search, generating new training pairs by modifying the current query to improve relevance modeling and understanding of user search behavior.

Contribution

It proposes a novel data augmentation method that alters the current query to create additional training pairs, capturing the symmetric relevance between session context and documents.

Findings

Enhanced model performance on public search logs

Effective learning of relevance variation with session context

Improved understanding of user search patterns

Abstract

Modeling contextual information in a search session has drawn more and more attention when understanding complex user intents. Recent methods are all data-driven, i.e., they train different models on large-scale search log data to identify the relevance between search contexts and candidate documents. The common training paradigm is to pair the search context with different candidate documents and train the model to rank the clicked documents higher than the unclicked ones. However, this paradigm neglects the symmetric nature of the relevance between the session context and document, i.e., the clicked documents can also be paired with different search contexts when training. In this work, we propose query-oriented data augmentation to enrich search logs and empower the modeling. We generate supplemental training pairs by altering the most important part of a search context, i.e., the current query, and train our model to rank the generated sequence along with the original sequence. This approach enables models to learn that the relevance of a document may vary as the session context changes, leading to a better understanding of users' search patterns. We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty. Through experimentation on two extensive public search logs, we have successfully demonstrated the effectiveness of our model.