PerspectroScope: A Window to the World of Diverse Perspectives
This system addresses the need for users to access varied perspectives on issues, though it appears incremental as it combines existing methods like retrieval and classifiers.
The authors tackled the problem of exploring diverse perspectives on discussion-worthy claims by developing PerspectroScope, a web-based system that extracts and visualizes supporting or opposing viewpoints with evidence, built using retrieval engines and learned classifiers.
This work presents PerspectroScope, a web-based system which lets users query a discussion-worthy natural language claim, and extract and visualize various perspectives in support or against the claim, along with evidence supporting each perspective. The system thus lets users explore various perspectives that could touch upon aspects of the issue at hand.The system is built as a combination of retrieval engines and learned textual-entailment-like classifiers built using a few recent developments in natural language understanding. To make the system more adaptive, expand its coverage, and improve its decisions over time, our platform employs various mechanisms to get corrections from the users. PerspectroScope is available at github.com/CogComp/perspectroscope.