TVShowGuess: Character Comprehension in Stories as Speaker Guessing
This work addresses the problem of narrative character comprehension for AI systems, representing an incremental step in this domain.
The authors introduced TVShowGuess, a task for evaluating machine understanding of fictional characters in TV show scripts by guessing anonymous main characters from scene backgrounds and dialogues, and found that their proposed models significantly outperformed baselines but still lagged far behind near-perfect human performance.
We propose a new task for assessing machines' skills of understanding fictional characters in narrative stories. The task, TVShowGuess, builds on the scripts of TV series and takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues. Our human study supports that this form of task covers comprehension of multiple types of character persona, including understanding characters' personalities, facts and memories of personal experience, which are well aligned with the psychological and literary theories about the theory of mind (ToM) of human beings on understanding fictional characters during reading. We further propose new model architectures to support the contextualized encoding of long scene texts. Experiments show that our proposed approaches significantly outperform baselines, yet still largely lag behind the (nearly perfect) human performance. Our work serves as a first step toward the goal of narrative character comprehension.