Saved in:
Bibliographic Details
Main Authors: Tang, Yixuan, Shi, Yuanyuan, Sun, Yiqun, Tung, Anthony Kum Hoe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.19758
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909759502811136
author Tang, Yixuan
Shi, Yuanyuan
Sun, Yiqun
Tung, Anthony Kum Hoe
author_facet Tang, Yixuan
Shi, Yuanyuan
Sun, Yiqun
Tung, Anthony Kum Hoe
contents Access to diverse perspectives is essential for understanding real-world events, yet most news retrieval systems prioritize textual relevance, leading to redundant results and limited viewpoint exposure. We propose NEWSCOPE, a two-stage framework for diverse news retrieval that enhances event coverage by explicitly modeling semantic variation at the sentence level. The first stage retrieves topically relevant content using dense retrieval, while the second stage applies sentence-level clustering and diversity-aware re-ranking to surface complementary information. To evaluate retrieval diversity, we introduce three interpretable metrics, namely Average Pairwise Distance, Positive Cluster Coverage, and Information Density Ratio, and construct two paragraph-level benchmarks: LocalNews and DSGlobal. Experiments show that NEWSCOPE consistently outperforms strong baselines, achieving significantly higher diversity without compromising relevance. Our results demonstrate the effectiveness of fine-grained, interpretable modeling in mitigating redundancy and promoting comprehensive event understanding. The data and code are available at https://github.com/tangyixuan/NEWSCOPE.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval
Tang, Yixuan
Shi, Yuanyuan
Sun, Yiqun
Tung, Anthony Kum Hoe
Computation and Language
Information Retrieval
Access to diverse perspectives is essential for understanding real-world events, yet most news retrieval systems prioritize textual relevance, leading to redundant results and limited viewpoint exposure. We propose NEWSCOPE, a two-stage framework for diverse news retrieval that enhances event coverage by explicitly modeling semantic variation at the sentence level. The first stage retrieves topically relevant content using dense retrieval, while the second stage applies sentence-level clustering and diversity-aware re-ranking to surface complementary information. To evaluate retrieval diversity, we introduce three interpretable metrics, namely Average Pairwise Distance, Positive Cluster Coverage, and Information Density Ratio, and construct two paragraph-level benchmarks: LocalNews and DSGlobal. Experiments show that NEWSCOPE consistently outperforms strong baselines, achieving significantly higher diversity without compromising relevance. Our results demonstrate the effectiveness of fine-grained, interpretable modeling in mitigating redundancy and promoting comprehensive event understanding. The data and code are available at https://github.com/tangyixuan/NEWSCOPE.
title Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2508.19758