Search Intenion Network for Personalized Query Auto-Completion in E-Commerce

TL;DR

Query Auto-Completion plays a key role in complementing user queries and helping them refine their search intentions, and today's QAC systems in real-world scenarios face two major challenges.

Abstract

Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions.Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process,the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model.2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer.However, the current intention extracted from prefix may be contrary to the historical preferences.

Figures (4)

• Figure 1: The schema of the proposed Search Intention Network (SIN).Followed by distilling information from the candidate query(1),entered prefix (2) and $\bf N$ kinds of user behavior sequences(3),SIN captures interest evolution between historical perference patterns and currently activated core interest(4),and finally conducts the CTR prediction task(5).
• Figure 2: Performance comparison of the baseline method adding different key designs.
• Figure 3: SIN performance by history lengths.
• Figure 4: The MRR performance of SIN over different numbers of embedding dimensions.