Event-enhanced Retrieval in Real-time Search

TL;DR

This paper introduces EER, a novel event-enhanced retrieval method that improves real-time search performance by focusing on key event information using contrastive and generative learning techniques, addressing semantic drift issues.

Contribution

The paper proposes a new event-enhanced retrieval approach that incorporates a decoder and generative triplet extraction to improve focus on key information in real-time search scenarios.

Findings

Significantly improved retrieval performance in real-time search.

Effective focus on crucial event information during retrieval.

Enhanced encoder optimization through contrastive and comparative learning.

Abstract

The embedding-based retrieval (EBR) approach is widely used in mainstream search engine retrieval systems and is crucial in recent retrieval-augmented methods for eliminating LLM illusions. However, existing EBR models often face the "semantic drift" problem and insufficient focus on key information, leading to a low adoption rate of retrieval results in subsequent steps. This issue is especially noticeable in real-time search scenarios, where the various expressions of popular events on the Internet make real-time retrieval heavily reliant on crucial event information. To tackle this problem, this paper proposes a novel approach called EER, which enhances real-time retrieval performance by improving the dual-encoder model of traditional EBR. We incorporate contrastive learning to accompany pairwise learning for encoder optimization. Furthermore, to strengthen the focus on critical event information in events, we include a decoder module after the document encoder, introduce a generative event triplet extraction scheme based on prompt-tuning, and correlate the events with query encoder optimization through comparative learning. This decoder module can be removed during inference. Extensive experiments demonstrate that EER can significantly improve the real-time search retrieval performance. We believe that this approach will provide new perspectives in the field of information retrieval. The codes and dataset are available at https://github.com/open-event-hub/Event-enhanced_Retrieval .