High Quality Real-Time Structured Debate Generation
This work addresses the problem of automatically generating high-quality, structured debates, which is relevant for AI systems that require sophisticated argumentation capabilities.
The authors propose a framework for generating structured debates in real-time by defining debate trees and paths. Their system generates debates on complex topics with quality close to human-level, as evaluated by style, content, and strategy metrics.
Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level structure and grammar. We leverage a large corpus of tree-structured debates that have metadata associated with each argument. We develop a framework for generating plausible debates which is agnostic to the sentence embedding model. Our results demonstrate the ability to generate debates in real-time on complex topics at a quality that is close to humans, as evaluated by the style, content, and strategy metrics used for judging competitive human debates. In the spirit of reproducible research we make our data, models, and code publicly available.