Unsupervised Discovery of Biographical Structure from Text

Unsupervised Discovery of Biographical Structure from Text David Bamman School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, USA dbamman@cs.cmu.edu Noah A. Smith School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, USA nasmith@cs.cmu.edu Abstract We present a method for discovering abstract event classes in biographies, based on a prob- abilistic latent-variable model. Taking as in- put timestamped text, we exploit latent corre- lations among events to learn a set of event classes (such as BORN, GRADUATES HIGH SCHOOL, and BECOMES CITIZEN), along with the typical times in a person’s life when those events occur. In a quantitative evalua- tion at the task of predicting a person’s age for a given event, we find that our genera- tive model outperforms a strong linear regres- sion baseline, along with simpler variants of the model that ablate some features. The ab- stract event classes that we learn allow us to perform a large-scale analysis of 242,970 Wikipedia biographies. Though it is known that women are greatly underrepresented on Wikipedia—not only as editors (Wikipedia, 2011) but also as subjects of articles (Reagle and Rhue, 2011)—we find that there is a bias in their characterization as well, with biogra- phies of women containing significantly more emphasis on events of marriage and divorce than biographies of men. 1 Introduction The written text that we interact with on an everyday basis—news articles, emails, social media, books— contains a vast amount of information centered on people: news (including common NLP corpora such as the New York Times and the Wall Street Journal) details the roles of actors in current events, social media (including Twitter and Facebook) documents the actions and attitudes of friends, and books chron- icle the stories of fictional characters and real people alike. This focus on people gives us an abundance of information on how the lives of those portrayed un- fold; for corpora that include historically deep bi- ographical information (such as Wikipedia, book- length biographies and autobiographies, and even newspaper obituaries) this data includes the actors involved in particular historical events and the times and places in which they occur. The life events de- scribed in these texts have natural structure: event classes exhibit correlations with each other (e.g., those who DIVORCE must have been MARRIED), can occur at roughly similar times in the lives of dif- ferent individuals (MARRIAGE is more likely to oc- cur earlier in one’s life than later), and can be bound to historical moments as well (FIGHTS IN WORLD WAR II peaks in the early 1940s). Social scientists have long been interested in the structure of these events in investigating the role that individual agency and larger social forces play in shaping the course of an individual’s life. Life stages marking “transitions to adulthood” (such as LEAVING SCHOOL, ENTERING THE WORKFORCE and MARRIAGE) have important correlates with de- mographic variables (Modell et al., 1976; Hogan and Astone, 1986; Shanahan, 2000); and researchers study the interactional effects that life events have on each other, such as …

Content truncated to 500 words