Integrating Semantics And Neighborhood Information With Graph-driven Generative Models For Document Retrieval

Abstract

With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale information retrieval. To generate high-quality hashing code, both semantics and neighborhood information are crucial. However, most existing methods leverage only one of them or simply combine them via some intuitive criteria, lacking a theoretical principle to guide the integration process. In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. To deal with the complicated correlations among documents, we further propose a tree-structured approximation method for learning. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones. Extensive experimental results on three benchm

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyou2021integrating

Related papers

• Document Hashing With Mixture-prior Generative Models (2019)7.50
• Variational Deep Semantic Hashing For Text Documents (2017)12.25
• Refining BERT Embeddings For Document Hashing Via Mutual Information Maximization (2021)3.58
• Generative Semantic Hashing Enhanced Via Boltzmann Machines (2020)3.58
• NASH: Toward End-to-end Neural Architecture For Generative Semantic Hashing (2018)10.07
• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Improving Document Representations By Generating Pseudo Query Embeddings For Dense Retrieval (2021)9.41
• Generative Retrieval As Multi-vector Dense Retrieval (2024)8.60