Multi-view Story Characterization from Movie Plot Synopses and Reviews

TL;DR

This paper presents a multi-view hierarchical attention model that characterizes movie stories by inferring themes and styles from synopses and reviews, improving attribute extraction without direct supervision.

Contribution

The paper introduces a novel multi-view model combining synopses and reviews for story characterization, enhancing attribute inference and enabling unsupervised extraction.

Findings

Improved attribute prediction over single-view methods

Effective multi-view encoding with hierarchical attention

Unsupervised extraction of story attributes from reviews

Abstract

This paper considers the problem of characterizing stories by inferring properties such as theme and style using written synopses and reviews of movies. We experiment with a multi-label dataset of movie synopses and a tagset representing various attributes of stories (e.g., genre, type of events). Our proposed multi-view model encodes the synopses and reviews using hierarchical attention and shows improvement over methods that only use synopses. Finally, we demonstrate how can we take advantage of such a model to extract a complementary set of story-attributes from reviews without direct supervision. We have made our dataset and source code publicly available at https://ritual.uh.edu/ multiview-tag-2020.