AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

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 and 4 more

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DocT5Query-generated training queries (ablation)NCI · NQ320kRecall@1: 60.23 -> 65.86Improved
add document-content queries (ablation)NCI · NQ320kRecall@1: 62.49 -> 65.86Improved
use the PAWA decoder instead of shared classifier weights (ablation)NCI · NQ320kRecall@1: 63.36 -> 65.86Improved
use hierarchical semantic identifiers instead of random identifiers (ablation)NCI · NQ320kRecall@1: 62.75 -> 65.86Improved
add consistency-based regularization (ablation)NCI · NQ320kRecall@1: 65.07 -> 65.86Improved
constrain beam search to valid identifiers (ablation)NCI · NQ320kRecall@1: 65.65 -> 65.86Improved
increase PAWA adapter depth from 0 to 4 layers (ablation)NCI · NQ320kRecall@1: 63.36 -> 65.86Improved
increase PAWA adapter depth from 4 to 8 layers (ablation)NCI · NQ320kRecall@1: 65.86 -> 63.60Hurt
set consistency-regularization weight α to 0.15 rather than 0 (ablation)NCI · NQ320kRecall@1: 65.07 -> 65.86Improved
increase consistency-regularization weight α from 0.15 to 0.2 (ablation)NCI · NQ320kRecall@1: 65.86 -> 65.55Hurt
use NCI w/ qg-ft ensemble instead of SEAL (Large)NQ320k · NQ320kRecall@1: 59.93 -> 72.78Improved
use NCI ensemble instead of SEAL (Large)TriviaQA · TriviaQAR-Precision: 69.2 -> 80.84Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy