Query-Focused Scenario Construction
This addresses the challenge of constructing coherent narratives from contradictory news reports, which is an incremental improvement over prior work.
The paper tackles the problem of extracting compatible sets of events from conflicting news accounts by developing a query-based system formulated as one-class clustering, which substantially outperforms baselines on a new human-curated dataset of real-world news topics.
The news coverage of events often contains not one but multiple incompatible accounts of what happened. We develop a query-based system that extracts compatible sets of events (scenarios) from such data, formulated as one-class clustering. Our system incrementally evaluates each event's compatibility with already selected events, taking order into account. We use synthetic data consisting of article mixtures for scalable training and evaluate our model on a new human-curated dataset of scenarios about real-world news topics. Stronger neural network models and harder synthetic training settings are both important to achieve high performance, and our final scenario construction system substantially outperforms baselines based on prior work.