From Generating to Mining: Automatically Scripting Conversations Using Existing Online Sources

Hearing people argue opposing sides of an issue can be a useful way to understand the topic; however, these debates or conversations often don't exist. Unfortunately, generating interesting natural language conversations is a difficult problem and typically requires a deep model of both a domain and its language. Fortunately, there is a huge amount of interesting text, written both by professional writers and amateurs, already available on the web. In this paper, we describe a system that builds compelling conversations between two characters-not by generating wholly new natural language, but by gathering, assembling, and processing existing online textual content. Our initial system authors conversations between two simulated movie reviewers, in a style similar to “Siskel and Ebert.” Using various online repositories, the system searches for a variety of facts and opinions about a given film. The system then uses this mined data to choose between various conversational templates and construct the dialogue. Using this information, the system is able to generate natural-sounding, colorful conversations and arguments without a deep representation of the subject being discussed.