CNTLS: A Benchmark Dataset for Abstractive or Extractive Chinese Timeline Summarization

TL;DR

This paper introduces CNTLS, the first Chinese timeline summarization dataset, enabling research on extractive and abstractive methods for long-event summarization with 77 topics and extensive document collections.

Contribution

The paper presents CNTLS, a comprehensive Chinese timeline summarization dataset with detailed analysis and benchmark results, filling a significant data gap in the field.

Findings

CNTLS covers 77 topics with 2524 documents each.

Benchmarking shows varied performance of summarization systems.

The dataset facilitates future research in Chinese timeline summarization.

Abstract

Timeline summarization (TLS) involves creating summaries of long-running events using dated summaries from numerous news articles. However, limited data availability has significantly slowed down the development of timeline summarization. In this paper, we introduce the CNTLS dataset, a versatile resource for Chinese timeline summarization. CNTLS encompasses 77 real-life topics, each with 2524 documents and summarizes nearly 60\% days duration compression on average all topics. We meticulously analyze the corpus using well-known metrics, focusing on the style of the summaries and the complexity of the summarization task. Specifically, we evaluate the performance of various extractive and generative summarization systems on the CNTLS corpus to provide benchmarks and support further research. To the best of our knowledge, CNTLS is the first Chinese timeline summarization dataset. The dataset and source code are released\footnote{Code and data available at: \emph{\url{https://github.com/OpenSUM/CNTLS}}.}.