Learn how IBM Project Debater works

Project Debater relies on three pioneering capabilities: data-driven speech writing and delivery, listening comprehension, and the modeling of human dilemmas.

How does Project Debater work?


Project Debater relies on three pioneering capabilities: data-driven speech writing and delivery, listening comprehension, and the modeling of human dilemmas.

how debater works infographic thumbnail image

Project Debater relies on three pioneering capabilities. The first is data-driven speech writing and delivery, or the ability to automatically generate a whole speech, reminiscent of an opinion article, and deliver it persuasively. The second is listening comprehension, which is the ability to understand a long spontaneous speech made by the human opponent in order to construct a meaningful rebuttal. The third is the system’s ability to model human dilemmas and form principled arguments made by humans in different debates based on a unique knowledge graph. By combining these core capabilities, it can conduct a meaningful debate with human debaters.

How Project Debater works

how debater works infographic

The basics

Step 1
Understanding a topic

Step 2
Argument construction

Step 3
Content organization

Step 4
Constructing an argument and rebuttal

Explore the technology

 

Argument Mining

Claims and evidence are the main components of an argument; identifying and using them correctly are essential to framing an argument in a debate. The IBM Project Debater team has invested substantial effort in developing machine learning techniques to mine massive corpora for claims and evidence and use them to generate arguments relevant to a controversial topic.

 

Detecting claims in relevant documents

Detecting evidence in relevant documents 

Negating claims

Synthesizing novel claims

Detecting claims throughout a corpus 

Improving corpus-wide claim detection 

Assessing argumentation quality

Relating arguments across texts

 

Stance Classification and Sentiment Analysis

An automatic debating system must be able to identify whether an argument supports or contests a given topic. This is fairly easy for humans but difficult for machines, as it requires great sensitivity to the rich subtleties and nuances of natural language. We have made important progress in this intriguing line of research.

 

Determining expert opinion stance

Determining claim stance 

Improving claim stance classification

Classifying sentiment of phrases

Classifying sentiment of idioms

 
 

Deep Neural Nets (DNNs) and Weak Supervision

DNNs hold immense potential for improving automatic understanding of language, but training them is notoriously known to require a lot of high quality, manually labeled data. We developed tools and methods to train DNNs using weak supervision, alleviating that bottleneck. We also used DNNs in developing Project Debater’s speaking and listening skills.

 

Scoring arguments

Understanding Automatic Speech Recognition (ASR) output

Predicting phrase breaks

Emphasizing words and phrases

Improving speech patterns 

Identifying similar sentences 

Improving argument mining

Searching for claims throughout a corpus

Determining concept abstractness

 
 

Text-to-Speech (TTS) Systems

Unlike a personal assistant or navigator, a debating system needs to speak continuously and persuasively for a few minutes on a subject not known in advance, while keeping the audience engaged. We developed new TTS algorithms and techniques to give Project Debater a clear, fluent, and persuasive voice.

 

Predicting phrase breaks

Emphasizing words and phrases 

Improving speech patterns

 
IBM Debater Speech by Crowd screenshot

Participate in a debate


Project Debater - Speech by Crowd, a new and experimental cloud-based AI platform for crowd-sourcing decision support. Project Debater - Speech by Crowd uses AI to collect free-text arguments from large audiences on debatable topics and automatically construct persuasive viewpoints to support or contest the topic. After the AI analyzes the arguments for their polarity, strength and relevance to the topic, the results are displayed on this indicator scale.

Should the Flu Vaccination be mandatory?

Join the debate

live debate

Learn more about how Project Debater

WEB

About 

Project Debater is the first AI system that can debate humans on complex topics. The goal is to help people build persuasive arguments and make well-informed decisions.

WEB

Importance

The world is awash with information, misinformation, and superficial thinking. Project Debater pushes the frontiers of AI to facilitate intelligent debate so we can build well-informed arguments and make better decisions.

WEB

Research

The Project Debater team has published technical work in various top quality scientific conference proceedings. So far, more than 30 works have been published, or are under review, in various research domains.

Research