Understanding Actors and Evaluating Personae with Gaussian Embeddings

TL;DR

This paper introduces a novel Gaussian embedding approach to model actors and their versatility in narrative content, enabling automatic evaluation of personae and improving over previous methods.

Contribution

It proposes a new actor-embedding technique using Gaussian distributions and translation vectors, along with two tasks for evaluating actors and personae.

Findings

The Gaussian embedding method outperforms TransE and baselines.

Automatically identified persona topics improve task performance.

Simple descriptors like age and gender are less effective.

Abstract

Understanding narrative content has become an increasingly popular topic. Nonetheless, research on identifying common types of narrative characters, or personae, is impeded by the lack of automatic and broad-coverage evaluation methods. We argue that computationally modeling actors provides benefits, including novel evaluation mechanisms for personae. Specifically, we propose two actor-modeling tasks, cast prediction and versatility ranking, which can capture complementary aspects of the relation between actors and the characters they portray. For an actor model, we present a technique for embedding actors, movies, character roles, genres, and descriptive keywords as Gaussian distributions and translation vectors, where the Gaussian variance corresponds to actors' versatility. Empirical results indicate that (1) the technique considerably outperforms TransE (Bordes et al. 2013) and ablation baselines and (2) automatically identified persona topics (Bamman, O'Connor, and Smith 2013) yield statistically significant improvements in both tasks, whereas simplistic persona descriptors including age and gender perform inconsistently, validating prior research.