TVSHOWGUESS: Character Comprehension in Stories as Speaker Guessing

Yisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, Jeffrey Stanton

Research output: Chapter in Book/Entry/PoemConference contribution

10 Scopus citations


We propose a new task for assessing machines' ability to understand 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 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.

Original languageEnglish (US)
Title of host publicationNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
StatePublished - 2022


Dive into the research topics of 'TVSHOWGUESS: Character Comprehension in Stories as Speaker Guessing'. Together they form a unique fingerprint.

Cite this