DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph
This work addresses the problem of accurately summarizing lengthy and nuanced movie scripts for applications like summarization and question-answering, though it appears incremental as it builds on existing graph and text fusion methods.
The authors tackled the challenge of summarizing movie screenplays by introducing DiscoGraMS, a character-aware discourse graph representation, which showed initial promising results in capturing complex relationships and improving summarization tasks.
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.