Presenting a New Dataset for the Timeline Generation Problem

TL;DR

This paper introduces a new publicly available dataset of news articles and timelines for entities, along with an evaluation methodology using ROUGE, to advance research in timeline generation.

Contribution

The paper provides the first standard dataset and evaluation framework for entity timeline generation, addressing previous lack of resources.

Findings

Google results outperform baselines in timeline quality

Dataset includes 18,793 articles for 39 entities

ROUGE effectively evaluates timeline quality

Abstract

The timeline generation task summarises an entity's biography by selecting stories representing key events from a large pool of relevant documents. This paper addresses the lack of a standard dataset and evaluative methodology for the problem. We present and make publicly available a new dataset of 18,793 news articles covering 39 entities. For each entity, we provide a gold standard timeline and a set of entity-related articles. We propose ROUGE as an evaluation metric and validate our dataset by showing that top Google results outperform straw-man baselines.