Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising
The retrieval system is a crucial module in e-commerce search advertising that matches user queries with ads. The diverse expressions of users often produce massive tail queries that cannot match merchant bidwords, leading to poor retrieval efficiency. Existing methods, such as query log mining and vector matching, fail to optimize relevance, authenticity, and ad revenue of the rewrite.
Authors
- Jingping Shao (ORCID: https://orcid.org/0000-0001-8555-2020)
- Zhangang Lin (ORCID: https://orcid.org/0000-0003-1379-5044)
- Chunyuan Yuan (ORCID: https://orcid.org/0000-0001-9794-5032)
- Z. A. Liu (ORCID: https://orcid.org/0009-0002-6838-850X)
- Xue Jiang (ORCID: https://orcid.org/0000-0001-6944-9031)
- Changping Peng (ORCID: https://orcid.org/0009-0002-2561-1919)
- Zheng Fang (ORCID: https://orcid.org/0000-0001-6691-0312)
- Yuan Li (ORCID: https://orcid.org/0000-0001-8595-453X)
- Ming Pang (ORCID: https://orcid.org/0000-0003-0454-0808)
- Zheng Luo (ORCID: https://orcid.org/0000-0001-7750-7115)
Institutions
- Jingdong (China) (CN)
- Peking University Shenzhen Hospital (CN)
Publication Details
- Published
- 2025-07-13
- DOI
- https://doi.org/10.1145/3726302.3731952
- Primary Topic
- Consumer Market Behavior and Pricing
- Type
- article
- Field-Weighted Citation Impact
- 0.00