# Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search

arXiv: https://arxiv.org/abs/2208.06150 · HTML: https://mlsanity.com/paper/2208.06150/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2022.

## Built on by (most cited first, 10 of 10)

- [EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce](https://mlsanity.com/paper/2308.06966/) (2023)
- [Generative Retrieval with Preference Optimization for E-commerce Search](https://mlsanity.com/paper/2407.19829/) (2024)
- [A Multi-Granularity Matching Attention Network for Query Intent Classification in E-commerce Retrieval](https://mlsanity.com/paper/2303.15870/) (2023)
- [Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval](https://mlsanity.com/paper/2407.21488/) (2024)
- [Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search](https://mlsanity.com/paper/2502.15990/) (2025)
- [Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition](https://mlsanity.com/paper/2503.04201/) (2025)
- [Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model](https://mlsanity.com/paper/2405.05606/) (2024)
- [Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification](https://mlsanity.com/paper/2308.09308/) (2023)
- [pEBR: A Probabilistic Approach to Embedding Based Retrieval](https://mlsanity.com/paper/2410.19349/) (2024)
- [OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning](https://mlsanity.com/paper/2603.02658/) (2026)

## Abstract (arXiv)

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) fine-tuned model from the official pre-trained BERT using general corpus, on both offline datasets and online system. We have open sourced our datasets for the sake of reproducibility and future works.