@inproceedings{wang2022a,
author = {Wang, Yujing and Hou, Yingyan and Wang, Haonan and Miao, Ziming and Wu, Shibin and Sun, Hao and Chen, Qi and Xia, Yuqing and Chi, Chengmin and Zhao, Guoshuai and Liu, Zheng and Xie, Xing and Sun, Hao Allen and Deng, Weiwei and Zhang, Qi and Yang, Mao},
title = {A Neural Corpus Indexer for Document Retrieval},
booktitle = {NeurIPS 2022},
year = {2022},
month = {November},
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 +17.6% 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 = {http://approjects.co.za/?big=en-us/research/publication/a-neural-corpus-indexer-for-document-retrieval/},
}