Automatic Event Salience Identification
This work addresses the understudied task of event salience identification for language understanding, offering incremental improvements in a domain-specific area.
The paper tackles the problem of identifying event salience in text by proposing two models based on content similarities and discourse relations, with the neural model significantly outperforming a frequency baseline and improving over the feature-based model.
Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper empirically studies the Event Salience task and proposes two salience detection models based on content similarities and discourse relations. The first is a feature based salience model that incorporates similarities among discourse units. The second is a neural model that captures more complex relations between discourse units. Tested on our new large-scale event salience corpus, both methods significantly outperform the strong frequency baseline, while our neural model further improves the feature based one by a large margin. Our analyses demonstrate that our neural model captures interesting connections between salience and discourse unit relations (e.g., scripts and frame structures).