DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph

TL;DR

DiscoGraMS introduces a novel character-aware discourse graph to improve movie screenplay summarization by capturing complex relationships and long-term dependencies better than existing transformer models.

Contribution

The paper presents DiscoGraMS, a new graph-based representation for screenplays that enhances summarization and other tasks by modeling character interactions and discourse structure.

Findings

Initial results show promise in preserving screenplay content

Graph-text fusion improves information retention

Method outperforms baseline transformer models in capturing relationships

Abstract

Summarizing movie screenplays presents a unique set of challenges compared to standard document summarization. Screenplays are not only lengthy, but also feature a complex interplay of characters, dialogues, and scenes, with numerous direct and subtle relationships and contextual nuances that are difficult for machine learning models to accurately capture and comprehend. Recent attempts at screenplay summarization focus on fine-tuning transformer-based pre-trained models, but these models often fall short in capturing long-term dependencies and latent relationships, and frequently encounter the "lost in the middle" issue. To address these challenges, we introduce DiscoGraMS, a novel resource that represents movie scripts as a movie character-aware discourse graph (CaD Graph). This approach is well-suited for various downstream tasks, such as summarization, question-answering, and salience detection. The model aims to preserve all salient information, offering a more comprehensive and faithful representation of the screenplay's content. We further explore a baseline method that combines the CaD Graph with the corresponding movie script through a late fusion of graph and text modalities, and we present very initial promising results.