Efficient Neural Query Auto Completion

By S. Wang et al
Published on Oct. 19, 2020
Read the original document by opening this link in a new tab.

Table of Contents

1. INTRODUCTION
2. RELATED WORK
2.1 Traditional Approaches for QAC
2.2 Deep Learning Approach for QAC
2.3 Neural Language Modeling
3. AN EFFICIENT NEURAL QUERY AUTO COMPLETION SYSTEM
3.1 Candidate Generation
3.2 Candidate Ranking
3.2.1 Comparison to State-of-the-Art Models

Summary

Efficient Neural Query Auto Completion by S. Wang et al presents a system that addresses challenges in Query Auto Completion (QAC) systems by proposing an efficient neural QAC system with effective context modeling. The paper discusses the importance of QAC in information retrieval tasks and the challenges faced in designing sophisticated language models for QAC. The system aims to increase recall of query candidates and improve ranking performance using neural networks. The proposed system shows significant improvement in relevance and latency, achieving a good balance between accuracy and efficiency.
×
This is where the content will go.