Event GDR: Event-Centric Generative Document Retrieval

TL;DR

Event GDR introduces an event-centric approach to generative document retrieval, leveraging event knowledge and taxonomy to improve document representation and identifier construction, resulting in significant performance gains.

Contribution

This paper presents a novel event-centric model that incorporates event knowledge and taxonomy into generative document retrieval, addressing key challenges in content correlation and semantic structure.

Findings

Significant improvement over baselines on two datasets

Effective integration of event knowledge enhances document representation

Explicit semantic structure in identifiers benefits retrieval accuracy

Abstract

Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1) neglecting inner-content correlation during document representation; (2) lacking explicit semantic structure during identifier construction. Nonetheless, events have enriched relations and well-defined taxonomy, which could facilitate addressing the above two challenges. Inspired by this, we propose Event GDR, an event-centric generative document retrieval model, integrating event knowledge into this task. Specifically, we utilize an exchange-then-reflection method based on multi-agents for event knowledge extraction. For document representation, we employ events and relations to model the document to guarantee the comprehensiveness and inner-content correlation. For identifier construction, we map the events to well-defined event taxonomy to construct the identifiers with explicit semantic structure. Our method achieves significant improvement over the baselines on two datasets, and also hopes to provide insights for future research.