CLNov 14, 2024

DTELS: Towards Dynamic Granularity of Timeline Summarization

arXiv:2411.09297v111 citationsh-index: 28Has Code
Originality Highly original
AI Analysis

This addresses the need for diverse granularity in tracking news topics, though it is incremental as it builds on existing timeline summarization methods.

The paper tackles the problem of inflexible timeline summarization in online news by introducing DTELS, a new paradigm for adaptive timelines based on user instructions, and establishes a benchmark showing that LLM-based solutions are effective but struggle with consistency.

The rapid proliferation of online news has posed significant challenges in tracking the continuous development of news topics. Traditional timeline summarization constructs a chronological summary of the events but often lacks the flexibility to meet the diverse granularity needs. To overcome this limitation, we introduce a new paradigm, Dynamic-granularity TimELine Summarization, (DTELS), which aims to construct adaptive timelines based on user instructions or requirements. This paper establishes a comprehensive benchmark for DTLES that includes: (1) an evaluation framework grounded in journalistic standards to assess the timeline quality across four dimensions: Informativeness, Granular Consistency, Factuality, and Coherence; (2) a large-scale, multi-source dataset with multiple granularity timeline annotations based on a consensus process to facilitate authority; (3) extensive experiments and analysis with two proposed solutions based on Large Language Models (LLMs) and existing state-of-the-art TLS methods. The experimental results demonstrate the effectiveness of LLM-based solutions. However, even the most advanced LLMs struggle to consistently generate timelines that are both informative and granularly consistent, highlighting the challenges of the DTELS task.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes