Literature DB >> 33731946

An autonomous debating system.

Noam Slonim1, Yonatan Bilu2, Carlos Alzate3, Roy Bar-Haim2, Ben Bogin2, Francesca Bonin3, Leshem Choshen2, Edo Cohen-Karlik2, Lena Dankin2, Lilach Edelstein2, Liat Ein-Dor2, Roni Friedman-Melamed2, Assaf Gavron2, Ariel Gera2, Martin Gleize3, Shai Gretz2, Dan Gutfreund2, Alon Halfon2, Daniel Hershcovich2, Ron Hoory2, Yufang Hou3, Shay Hummel2, Michal Jacovi2, Charles Jochim3, Yoav Kantor2, Yoav Katz2, David Konopnicki2, Zvi Kons2, Lili Kotlerman2, Dalia Krieger2, Dan Lahav2, Tamar Lavee2, Ran Levy2, Naftali Liberman2, Yosi Mass2, Amir Menczel2, Shachar Mirkin2, Guy Moshkowich2, Shila Ofek-Koifman2, Matan Orbach2, Ella Rabinovich2, Ruty Rinott2, Slava Shechtman2, Dafna Sheinwald2, Eyal Shnarch2, Ilya Shnayderman2, Aya Soffer2, Artem Spector2, Benjamin Sznajder2, Assaf Toledo2, Orith Toledo-Ronen2, Elad Venezian2, Ranit Aharonov2.   

Abstract

Artificial intelligence (AI) is defined as the ability of machines to perform tasks that are usually associated with intelligent beings. Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activities, and common to all human societies. The development of computational argumentation technologies is therefore an important emerging discipline in AI research1. Here we present Project Debater, an autonomous debating system that can engage in a competitive debate with humans. We provide a complete description of the system's architecture, a thorough and systematic evaluation of its operation across a wide range of debate topics, and a detailed account of the system's performance in its public debut against three expert human debaters. We also highlight the fundamental differences between debating with humans as opposed to challenging humans in game competitions, the latter being the focus of classical 'grand challenges' pursued by the AI research community over the past few decades. We suggest that such challenges lie in the 'comfort zone' of AI, whereas debating with humans lies in a different territory, in which humans still prevail, and for which novel paradigms are required to make substantial progress.

Entities:  

Mesh:

Year:  2021        PMID: 33731946     DOI: 10.1038/s41586-021-03215-w

Source DB:  PubMed          Journal:  Nature        ISSN: 0028-0836            Impact factor:   49.962


  3 in total

1.  Why a Virtual Assistant for Moral Enhancement When We Could have a Socrates?

Authors:  Francisco Lara
Journal:  Sci Eng Ethics       Date:  2021-06-29       Impact factor: 3.525

2.  Toward audience-aware argument generation.

Authors:  Milad Alshomary; Henning Wachsmuth
Journal:  Patterns (N Y)       Date:  2021-06-11

Review 3.  Nobel Turing Challenge: creating the engine for scientific discovery.

Authors:  Hiroaki Kitano
Journal:  NPJ Syst Biol Appl       Date:  2021-06-18
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.