IRCLAug 8, 2022

Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval

Microsoft
arXiv:2208.04232v17 citationsh-index: 102Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for more effective and efficient document retrieval in information retrieval systems, though it appears incremental as it builds on existing dual-encoder models.

The paper tackles the problem of improving dense retrieval by learning diverse document representations through deep query interactions, resulting in a model that outperforms strong dual encoder baselines on several benchmarks.

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view document representations. It not only enjoys high inference efficiency like the vanilla dual-encoder models, but also enables deep query-document interactions in document encoding and provides multi-faceted representations to better match different queries. Experiments on several benchmarks demonstrate the effectiveness of the proposed method, out-performing strong dual encoder baselines.The code is available at \url{https://github.com/jordane95/dual-cross-encoder

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes