Hierarchical Encoders for Modeling and Interpreting Screenplays
This work addresses the problem of modeling structured documents like screenplays for researchers in NLP, though it is incremental as it adapts existing hierarchical encoding ideas to a specific domain.
The authors tackled the challenge of natural language understanding for long-form structured documents by proposing a neural architecture for encoding movie scripts, achieving robust performance on multi-label tag classification datasets without handcrafted features.
While natural language understanding of long-form documents is still an open challenge, such documents often contain structural information that can inform the design of models for encoding them. Movie scripts are an example of such richly structured text - scripts are segmented into scenes, which are further decomposed into dialogue and descriptive components. In this work, we propose a neural architecture for encoding this structure, which performs robustly on a pair of multi-label tag classification datasets, without the need for handcrafted features. We add a layer of insight by augmenting an unsupervised "interpretability" module to the encoder, allowing for the extraction and visualization of narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.