Pre-training Tasks For User Intent Detection And Embedding Retrieval In E-commerce Search
2022 · Yiming Qiu, Chenyu Zhao, Han Zhang, et al.
Abstract
BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. However, this technique may not always work, especially for two scenarios: a corpus that contains very different text from the general corpus Wikipedia, or a task that learns embedding spacial distribution for a specific purpose (e.g., approximate nearest neighbor search). In this paper, to tackle the above two scenarios that we have encountered in an industrial e-commerce search system, we propose customized and novel pre-training tasks for two critical modules: user intent detection and semantic embedding retrieval. The customized pre-trained models after fine-tuning, being less than 10% of BERT-base's size in order to be feasible for cost-efficient CPU serving, significantly improve the other baseline models: 1) no pre-training model and 2
Authors
(none)
Tags
Stats
Related papers
- Unified Embedding Based Personalized Retrieval In Etsy Search (2023)2.26
- Enterpriseem: Fine-tuned Embeddings For Enterprise Semantic Search (2024)0.00
- Retrieval-grpo: A Multi-objective Reinforcement Learning Framework For Dense Retrieval In Taobao Search (2025)0.00
- Pre-training Tasks For Embedding-based Large-scale Retrieval (2020)0.00
- Embedding-based Product Retrieval In Taobao Search (2021)13.70
- Mine And Refine: Optimizing Graded Relevance In E-commerce Search Retrieval (2026)0.00
- MAKE: Vision-language Pre-training Based Product Retrieval In Taobao Search (2023)7.81
- Delving Into E-commerce Product Retrieval With Vision-language Pre-training (2023)6.77