CPS-MEBR: Click Feedback-Aware Web Page Summarization for Multi-Embedding-Based Retrieval

TL;DR

This paper introduces CPS-MEBR, a web page summarization framework that generates multiple embeddings based on user click data to improve retrieval accuracy for complex web pages.

Contribution

It proposes a novel multi-embedding retrieval model trained on click data, enhancing web page representation for better search relevance.

Findings

Outperforms single-embedding retrieval in candidate quality

Uses click data to identify key sentences for summarization

Employs sentence-level semantic interaction for multiple embeddings

Abstract

Embedding-based retrieval (EBR) is a technique to use embeddings to represent query and document, and then convert the retrieval problem into a nearest neighbor search problem in the embedding space. Some previous works have mainly focused on representing the web page with a single embedding, but in real web search scenarios, it is difficult to represent all the information of a long and complex structured web page as a single embedding. To address this issue, we design a click feedback-aware web page summarization for multi-embedding-based retrieval (CPS-MEBR) framework which is able to generate multiple embeddings for web pages to match different potential queries. Specifically, we use the click data of users in search logs to train a summary model to extract those sentences in web pages that are frequently clicked by users, which are more likely to answer those potential queries. Meanwhile, we introduce sentence-level semantic interaction to design a multi-embedding-based retrieval (MEBR) model, which can generate multiple embeddings to deal with different potential queries by using frequently clicked sentences in web pages. Offline experiments show that it can perform high quality candidate retrieval compared to single-embedding-based retrieval (SEBR) model.