{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dptdr-deep-prompt-tuning-for-dense-passage","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","arxiv_id":"2208.11503","date":"2022-08-24","proceeding":"COLING 2022 10","authors":["Zhengyang Tang","Benyou Wang","Ting Yao"],"abstract":"Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using the same backbone model~(e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval largely underperforms FT methods. To compensate for the performance drop, we propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining, as a general approach that could be compatible with any pre-trained language model and retrieval task. The experimental results show that the proposed method (called DPTDR) outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions. We also conduct ablation studies to examine the effectiveness of each strategy in DPTDR. We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources. Our code is available at https://github.com/tangzhy/DPTDR.","url_abs":"https://arxiv.org/abs/2208.11503v1","url_pdf":"https://arxiv.org/pdf/2208.11503v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dptdr-deep-prompt-tuning-for-dense-passage","repo_url":"https://github.com/tangzhy/dptdr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"dptdr-deep-prompt-tuning-for-dense-passage","repo_url":"https://github.com/MindSpore-scientific/code-7/tree/main/DPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-prediction-transformer","method_name":"DPT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.11503","atlas_url":"https://app.syntology.ai/?focus=2208.11503","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}