Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning

TL;DR

This paper introduces a contrastive learning-based relevance model for smartphone feature search that understands contextual queries and is optimized for on-device deployment, outperforming existing search methods.

Contribution

The paper presents a novel on-device retrieval system using contrastive learning and knowledge distillation to improve contextual feature search on smartphones.

Findings

Outperforms baseline search methods on contextual queries

Effective model compression with minimal performance loss

Enhances user experience in finding smartphone features

Abstract

The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short, and there are just too many to remember. In such a case, the users may want to ask contextual queries that describe the features they are looking for, but the standard term frequency-based search cannot process them. This paper presents a novel retrieval system for mobile features that accepts intuitive and contextual search queries. We trained a relevance model via contrastive learning from a pre-trained language model to perceive the contextual relevance between query embeddings and indexed mobile features. Also, to make it run efficiently on-device using minimal resources, we applied knowledge distillation to compress the model without degrading much performance. To verify the feasibility of our method, we collected test queries and conducted comparative experiments with the currently deployed search baselines. The results show that our system outperforms the others on contextual sentence queries and even on usual keyword-based queries.