News Article Retrieval in Context for Event-centric Narrative Creation

TL;DR

This paper addresses the challenge of retrieving relevant news articles to support event-centric narrative creation, proposing a new dataset and demonstrating that combining lexical, semantic, and chronological ranking improves retrieval performance.

Contribution

It introduces a formal task definition, a dataset construction method, and shows that combining different ranking strategies enhances news article retrieval for narratives.

Findings

Chronological ranking improves retrieval results.

Lexical and semantic rankers alone are insufficient.

Combined ranking methods outperform individual approaches.

Abstract

Writers such as journalists often use automatic tools to find relevant content to include in their narratives. In this paper, we focus on supporting writers in the news domain to develop event-centric narratives. Given an incomplete narrative that specifies a main event and a context, we aim to retrieve news articles that discuss relevant events that would enable the continuation of the narrative. We formally define this task and propose a retrieval dataset construction procedure that relies on existing news articles to simulate incomplete narratives and relevant articles. Experiments on two datasets derived from this procedure show that state-of-the-art lexical and semantic rankers are not sufficient for this task. We show that combining those with a ranker that ranks articles by reverse chronological order outperforms those rankers alone. We also perform an in-depth quantitative and qualitative analysis of the results that sheds light on the characteristics of this task.