Enhanced Representation with Contrastive Loss for Long-Tail Query Classification in e-commerce

Lvxing Zhu, Hao Chen, Chao Wei, Weiru Zhang


Abstract
Query classification is a fundamental task in an e-commerce search engine, which assigns one or multiple predefined product categories in response to each search query. Taking click-through logs as training data in deep learning methods is a common and effective approach for query classification. However, the frequency distribution of queries typically has long-tail property, which means that there are few logs for most of the queries. The lack of reliable user feedback information results in worse performance of long-tail queries compared with frequent queries. To solve the above problem, we propose a novel method that leverages an auxiliary module to enhance the representations of long-tail queries by taking advantage of reliable supervised information of variant frequent queries. The long-tail queries are guided by the contrastive loss to obtain category-aligned representations in the auxiliary module, where the variant frequent queries serve as anchors in the representation space. We train our model with real-world click data from AliExpress and conduct evaluation on both offline labeled data and online AB test. The results and further analysis demonstrate the effectiveness of our proposed method.
Anthology ID:
2022.ecnlp-1.17
Volume:
Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Shervin Malmasi, Oleg Rokhlenko, Nicola Ueffing, Ido Guy, Eugene Agichtein, Surya Kallumadi
Venue:
ECNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
141–150
Language:
URL:
https://aclanthology.org/2022.ecnlp-1.17
DOI:
10.18653/v1/2022.ecnlp-1.17
Bibkey:
Cite (ACL):
Lvxing Zhu, Hao Chen, Chao Wei, and Weiru Zhang. 2022. Enhanced Representation with Contrastive Loss for Long-Tail Query Classification in e-commerce. In Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5), pages 141–150, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Enhanced Representation with Contrastive Loss for Long-Tail Query Classification in e-commerce (Zhu et al., ECNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2022.ecnlp-1.17.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2022.ecnlp-1.17.mp4