Identifying Informational Sources in News Articles
This work addresses the need to understand and assist in news reporting by providing tools for journalists and narrative science, though it is incremental in building on existing data annotation efforts.
The authors tackled the problem of modeling informational sources in news articles by constructing the largest annotated dataset to date, and demonstrated its utility for training high-performing models for information detection, source attribution, and a novel source prediction task.
News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We show that our dataset can be used to train high-performing models for information detection and source attribution. We further introduce a novel task, source prediction, to study the compositionality of sources in news articles. We show good performance on this task, which we argue is an important proof for narrative science exploring the internal structure of news articles and aiding in planning-based language generation, and an important step towards a source-recommendation system to aid journalists.