Close-set Companies and Corpus-wide Claims (News, Economics and AI meetup)

#1 Close Set Extraction: Discovering Companies We Know
* by Rani Shlivinski *

Slides: Closed Set Extracyion for Meetup – March 2019

#2 Project Debater and Corpus-wide Claim Detection
* by Shai Gretz *

Project Debater is the first AI system developed to compete in a full-live debate with a human debater. The project, an IBM Grand Challenge developed in the company’s Haifa Research lab, is designed to build coherent, convincing speeches on its own, as well as provide rebuttals to the opponent’s main arguments. A few weeks ago, Project Debater competed against Harish Natarajan, a grand finalist in the 2016 Debating World Championships, in an event held in San Francisco and broadcasted live world-wide.
In this talk we will tell the story of Project Debater, from conception to a climatic final event, and describe its underlying technology. We will then discuss in more detail work done regarding a key component of Project Debater, corpus-wide claim detection.

Bio:

Shai Gretz joined Project Debater (and IBM) a little over 3 years ago, and has since worked on various NLP projects in the field of computational argumentation. Before joining IBM, Shai led the NLP work in the startup Wibbitz, after completing his M.Sc. in computer science in the field of NLP at the Technion.