{"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/a-neural-corpus-indexer-for-document","title":"A Neural Corpus Indexer for Document Retrieval","arxiv_id":"2206.02743","date":"2022-06-06","proceeding":null,"authors":["Yujing Wang","Yingyan Hou","Haonan Wang","Ziming Miao","Shibin Wu","Hao Sun","Qi Chen","Yuqing Xia","Chengmin Chi","Guoshuai Zhao","Zheng Liu","Xing Xie","Hao Allen Sun","Weiwei Deng","Qi Zhang","Mao Yang"],"abstract":"Current state-of-the-art document retrieval solutions mainly follow an index-retrieve paradigm, where the index is hard to be directly optimized for the final retrieval target. In this paper, we aim to show that an end-to-end deep neural network unifying training and indexing stages can significantly improve the recall performance of traditional methods. To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query. To optimize the recall performance of NCI, we invent a prefix-aware weight-adaptive decoder architecture, and leverage tailored techniques including query generation, semantic document identifiers, and consistency-based regularization. Empirical studies demonstrated the superiority of NCI on two commonly used academic benchmarks, achieving +21.4% and +16.8% relative enhancement for Recall@1 on NQ320k dataset and R-Precision on TriviaQA dataset, respectively, compared to the best baseline method.","url_abs":"https://arxiv.org/abs/2206.02743v3","url_pdf":"https://arxiv.org/pdf/2206.02743v3.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":"a-neural-corpus-indexer-for-document","repo_url":"https://github.com/solidsea98/neural-corpus-indexer-nci","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.02743","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}