Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories
This work addresses the challenge of understanding narrative structures in long texts for literary analysis and computational linguistics, though it appears incremental as it builds on existing unsupervised methods.
The paper tackled the problem of measuring event salience in long-form stories by improving a transformer language model with external knowledge and memory mechanisms, resulting in enhanced performance over baseline models on a novel dataset derived from classic literary works.
Measuring event salience is essential in the understanding of stories. This paper takes a recent unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise and applies it to longer narrative forms. We improve the standard transformer language model by incorporating an external knowledgebase (derived from Retrieval Augmented Generation) and adding a memory mechanism to enhance performance on longer works. We use a novel approach to derive salience annotation using chapter-aligned summaries from the Shmoop corpus for classic literary works. Our evaluation against this data demonstrates that our salience detection model improves performance over and above a non-knowledgebase and memory augmented language model, both of which are crucial to this improvement.