A Neural Corpus Indexer for Document Retrieval
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 Sun · Weiwei Deng · Qi Zhang · Mao Yang
Hall J (level 1) #242
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.