aRgumentation tHeory And natural language ProceSSing fOr e-DemocracY (RHAPSSODY)

PIs:

• Mihai Surdeanu, Computer Science, UArizona

• Srdjan Vesic, University of Artois

The RHAPSSODY project proposes an automated reasoning platform to extract, understand, and reason with complex arguments. The project is based on combining computational argumentation theory with natural language processing. This approach will identify the most essential arguments listed on debate platforms, estimate the acceptability degrees of these arguments using information mined from the web, and using the totality of the arguments (those from the particular debate and those mined from the other websites), estimate the decision that will be taken. One of the benefits of the project is that it can display the most important arguments to a newcomer (in debates where there can be hundreds of arguments), as well as underline the links between the arguments (such as attacks or supports), which help to better understand a debate.