Unsupervised Discovery of Biographical Structure from Text

• Published in: Transactions of the Association for Computational Linguistics Vol. 2; pp. 363 - 376
• Main Authors: Bamman, David, Smith, Noah A.
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.12.2014; MIT Press Journals, The; The MIT Press
• Subjects: Ablation; Biographies; Computer generated language analysis; Encyclopedias; Gender; Statistical analysis; Websites
• ISSN: 2307-387X; 2307-387X
• DOI: 10.1162/tacl_a_00189

We present a method for discovering abstract event classes in biographies, based on a probabilistic latent-variable model. Taking as input timestamped text, we exploit latent correlations among events to learn a set of event classes (such as B , G H S , and B C ), along with the typical times in a person’s life when those events occur. In a quantitative evaluation at the task of predicting a person’s age for a given event, we find that our generative model outperforms a strong linear regression baseline, along with simpler variants of the model that ablate some features. The abstract 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 as well, with biographies of women containing significantly more emphasis on events of marriage and divorce than biographies of men.