Paper Link: https://openreview.net/forum?id=NbQ0o6dC6oO
Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)
Abstract: 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.
Copyright Consent Signature (type Name Or NA If Not Transferrable): Yisi Sang
Copyright Consent Name And Address: Syracuse University, 900 South Crouse Ave. Syracuse, NY 13244
Presentation Mode: This paper will be presented in person in Seattle
0 Replies
Loading