Deep Pairwise Learning To Rank For Search Autocomplete

2021/08/11 by Yuan, Kai, Kuang, Da
#FOS: Computer and information sciences #H.4 #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2108.04976

Abstract

Autocomplete (a.k.a "Query Auto-Completion", "AC") suggests full queries based on a prefix typed by customer. Autocomplete has been a core feature of commercial search engine. In this paper, we propose a novel context-aware neural network based pairwise ranker (DeepPLTR) to improve AC ranking, DeepPLTR leverages contextual and behavioral features to rank queries by minimizing a pairwise loss, based on a fully-connected neural network structure. Compared to LambdaMART ranker, DeepPLTR shows +3.90% MeanReciprocalRank (MRR) lift in offline evaluation, and yielded +0.06% (p < 0.1) Gross Merchandise Value (GMV) lift in an Amazon's online A/B experiment.

Related

• Synthetic Prefixes to Mitigate Bias in Real-Time Neural Query Autocomplete
• From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search
• Accelerating E-Commerce Search Engine Ranking by Contextual Factor Selection
• Context-Aware Learning to Rank with Self-Attention
• Deploying Deep Ranking Models for Search Verticals