Project Debater APIs: Decomposing the AI Grand Challenge
This work provides tools for researchers and developers to build practical solutions in NLP and argument analysis, though it is incremental in offering APIs based on existing Project Debater components.
The paper tackles the challenge of decomposing AI debate capabilities into accessible APIs, including core NLP and argument mining services, and introduces Key Point Analysis for identifying main points in text collections, with performance metrics described for these services.
Project Debater was revealed in 2019 as the first AI system that can debate human experts on complex topics. Engaging in a live debate requires a diverse set of skills, and Project Debater has been developed accordingly as a collection of components, each designed to perform a specific subtask. Project Debater APIs provide access to many of these capabilities, as well as to more recently developed ones. This diverse set of web services, publicly available for academic use, includes core NLP services, argument mining and analysis capabilities, and higher-level services for content summarization. We describe these APIs and their performance, and demonstrate how they can be used for building practical solutions. In particular, we will focus on Key Point Analysis, a novel technology that identifies the main points and their prevalence in a collection of texts such as survey responses and user reviews.