Learning Latent Personas of Film Characters

By David Bamman, Brendan T. O'Connor, Noah A. Smith. 2013

276 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences (2018, background): “Fiction: [277] • Stories from the Gutenberg project • Children stories from MCTest (Richard- son et al., 2013) • Movie plots from CMU Movie Sum- mary corpus (Bamman et al., 2013) From each of the above-mentioned sources we extracted paragraphs that had enough content.”
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, methodology): “Formal probabilistic models have also been proposed to learn event schemas and frames (Che-ung et al., 2013; Bamman et al., 2013; Chambers, 2013; Nguyen et al., 2015).”
Posterior calibration and exploratory analysis for natural language processing models (2015, background): “But these systems are accurate enough so that their outputs can be used as soft, if noisy, indicators of language meaning for use in downstream analysis, such as systems that perform question answering, machine translation, event extraction, and narrative analysis (McCord et al., 2012; Gimpel and Sm”
Understanding the Shades of Sexism in Popular TV Series (2019, methodology): “Secondly, we determine characters with sexist tropes based on the character-trope mappings obtained from two sources: TVTropes.com and Character Tropes Dataset (Bamman et al., 2013).”
Entity-Centric Contextual Affective Analysis (2019, methodology): “Following Bamman et al. (2013), we analyze the Wikipedia plot summary of the movie The Dark Knight,7 focusing on Batman (protagonist),8 the Joker (antagonist), Jim Gordan (law enforcement officer, ally to Batman), Har-”
A Bayesian Mixed Effects Model of Literary Character (2014, methodology): “In contrast, the Persona Regression model of Bamman et al. (2013), which uses metadata variables (like authorship) to encourage entities with similar covariates to have similar personas, reflects an assumption that makes it likely to perform well at class B.”
Gender and Representation Bias in GPT-3 Generated Stories (2021, background): “Words linked to people via linguistic dependencies can be used to analyze descriptions of people in text (Fast et al., 2016b; Hoyle et al., 2019; Lucy et al., 2020; Bamman et al., 2013; Sap et al., 2017).”
Statistical Script Learning with Multi-Argument Events (2014, background): “Bamman et al. (2013) learn latent character personas from film summaries, associating character types with stereotypical actions; they focus on identifying persona types, rather than event inference.”
Event Representations for Automated Story Generation with Deep Neural Nets (2017, methodology): “For this work, we use a corpus of movie plot summaries extracted from Wikipedia (Bamman, O’Connor, and Smith 2014) under the premise that the set of movies plots on Wikipedia covers the range of topics that people want to tell stories about.”
Controllable Neural Story Generation via Reinforcement Learning (2018, methodology): “We use the CMU movie summary corpus (Bamman, O’Connor, and Smith 2014), which contains 42,170 stories that are on average 14.515 lines long.”
Story Comprehension for Predicting What Happens Next (2017, methodology): “These methods study character personas (Bamman et al., 2013, 2014) or Prop-pian (Propp, 1968) roles (Valls-Vargas et al., 2014, 2015), inter-character relationships (Iyyer et al., 2016; Chaturvedi et al., 2016, 2017), and social networks of characters (Elson et al., 2010; Elson, 2012; Agarwal et…”
Movie Script Summarization as Graph-based Scene Extraction (2015, methodology): “Other work (Bamman et al., 2013, 2014) automatically infers latent character types (e.g., villains or heroes) in novels and movie plot summaries.”
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels (2017, methodology): “Unsupervised models have been proposed which, given raw text, extract prototypical event structure (McIntyre and Lapata, 2010; Chambers and Jurafsky, 2009), prototypical characters (Bamman et al., 2013, 2014; Elsner, 2012) and their social networks (Elson et al., 2010).”
Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models (2023, background): “Our term “persona” draws upon the linguistics notion of “persona” as more malleable and constructed-in-the-moment than “identity” (Podesva et al., 2015) and on the HCI use of “persona” as a model of a hypothetical individual (Cooper, 1999; Blomkvist, 2002; Jettmar and Nass, 2002; Muller and Carey, 2”
Facts2Story: Controlling Text Generation by Key Facts (2020, methodology): “We use a large corpus of movie plots taken from Wikipedia (Robischon, 2015; Bamman et al., 2013) as they also conform to similar lengths and format.”