Authors: Shengjia Cui; Xianglong Qi; Xiao Wang; Chen Zeng
Addresses: Shengjia Cui Baidu Co., Ltd., Beijing, China ' Liaoning Huading Technology Co., Ltd., Liaoning, China ' Baidu Co., Ltd., Beijing, China ' Baidu Co., Ltd., Beijing, China
Abstract: Although user intention detection has been widely studied, existing researches suffer inferior performance when only utilising the semantic features of query and neglecting the personalised user attributes. A key challenge is that the same or similar queries among users who possess different social positions can be inferred from different intentions. Therefore, we propose a novel task that user attributes are introduced as additional personalised features in user intention detection besides the semantic information of queries, named 'Persona User Intention Detection (PUID)'. We collected the query log with corresponding user attributes on the professional search engine to construct a large-scale user intention data set. Then, we propose a Persona-Augmented Hypergraph Neural Network (PAHG) for PUID consequently. Extensive experiments are conducted on several state-of-the-art methods and our method. The experimental results demonstrate that our method outperforms others, fulfills the requirement of real-world scenario and improves the user experience further.
Keywords: intent detection; hypergraph learning; large-scale modelling.
International Journal of Computer Applications in Technology, 2022 Vol.70 No.1, pp.1 - 10
Received: 12 Nov 2021
Accepted: 14 Dec 2021
Published online: 03 Apr 2023 *