News Article Retrieval in Context for Event-centric Narrative Creation
This addresses a specific need for journalists and writers in the news domain by improving content retrieval for narrative creation, though it is incremental as it builds on existing ranking methods.
The paper tackled the problem of retrieving relevant news articles to help writers continue event-centric narratives, showing that combining lexical and semantic rankers with reverse chronological ordering outperforms state-of-the-art rankers alone.
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.