Article Structure
Abstract
We present two latent variable models for learning character types, or personas, in film, in which a persona is defined as a set of mixtures over latent lexical classes.
Introduction
Philosophers and dramatists have long argued whether the most important element of narrative is plot or character.
Data
2.1 Text
Personas
One way we recognize a character’s latent type is by observing the stereotypical actions they
Models
Both models that we present here simultaneously learn three things: 1.)
Evaluation
We evaluate our methods in two quantitative ways by measuring the degree to which we recover two different sets of gold-standard clusterings.
Exploratory Data Analysis
As with other generative approaches, latent persona models enable exploratory data analysis.
Conclusion
We present a method for automatically inferring latent character personas from text (and metadata, when available).
Topics
regression model
- Distribution over topics for persona p in role 7“ 0d Movie d’s distribution over personas pe Character e’s persona (integer, p E {1..P}) j A specific (7“, w) tuple in the data Zj Word topic for tuple j 1113' Word for tuple j oz Concentration parameter for Dirichlet model 6 Feature weights for regression model [1,02 Gaussian mean and variance (for regularizing B) md Movie features (from movie metadata) me Entity features (from movie actor metadata) VT, 7 Dirichlet concentration parametersPage 3, “Models”
- Figure 2: Above: Dirichlet persona model (left) and persona regression model (right).Page 3, “Models”
- The difference between the persona regression model and the Dirichlet persona model here is notPage 6, “Evaluation”
- by the persona regression model , along with links fnPage 7, “Evaluation”
- In practice, we find that while the Dirichlet model distinguishes between character personas in different movies, the persona regression model helps distinguish between different personas within the same movie.Page 7, “Evaluation”
- To illustrate this, we present results from the persona regression model learned above, with 50 latent lexical classes and 100 latent personas.Page 7, “Exploratory Data Analysis”
See all papers in Proc. ACL 2013 that mention regression model.
See all papers in Proc. ACL that mention regression model.
Back to top.
clusterings
- We evaluate our methods in two quantitative ways by measuring the degree to which we recover two different sets of gold-standard clusterings .Page 5, “Evaluation”
- To measure the similarity between the two clusterings of movie characters, gold clusters Q and induced latent persona clusters C, we calculate the variation of information (Meila, 2007):Page 5, “Evaluation”
- VI measures the information-theoretic distance between the two clusterings : a lower value means greater similarity, and VI = 0 if they are identical.Page 5, “Evaluation”
- Over all tests in comparison to both gold clusterings , we see VI improve as both P and, to a lesser extent, K increase.Page 6, “Evaluation”
- significant; while VI allows us to compare models with different numbers of latent clusters, its requirement that clusterings be mutually informative places a high overhead on models that are fundamentally unidirectional (in Table l, for example, the room for improvement between two models of the same P and K is naturally smaller than the bigger difference between different P or K).Page 6, “Evaluation”
See all papers in Proc. ACL 2013 that mention clusterings.
See all papers in Proc. ACL that mention clusterings.
Back to top.
hyperparameter
- P Number of personas (hyperparameter) K Number of word topics ( hyperparameter ) D Number of movie plot summaries E Number of characters in movie d W Number of (role, word) tuples used by character 6 (bk Topic kr’s distribution over V words.Page 3, “Models”
- Next, let a persona p be defined as a set of three multinomials $10 over these K topics, one for each typed role 7“, each drawn from a Dirichlet with a role-specific hyperparameter (VT).Page 4, “Models”
- In other words, the probability that character 6 embodies persona k is proportional to the number of other characters in the plot summary who also embody that persona (plus the Dirichlet hyperparameter 0%) times the contribution of each observed word wj for that character, given its current topic assignment zj.Page 4, “Models”
See all papers in Proc. ACL 2013 that mention hyperparameter.
See all papers in Proc. ACL that mention hyperparameter.
Back to top.
