‘F’ to ‘A’ on the N.Y. Regents Science Exams: An Overview of the Aristo Project

Performing well on standardized exams has been a longstanding challenge for AI. Even in 2016, the best AI system achieved less than 60% on an 8th Grade science exam challenge. Recently, AI2’s Aristo system achieved surprising success on the Grade 8 New York Regents Science Exams, scoring over 90% on the exam’s non-diagram, multiple choice (NDMC) questions. How was it able to do this, and what mistakes does it still make? In this talk, I will overview Aristo and the impact of its various components, in particular, its new language model (LM) solvers. I will also present several analyses of what is going on inside Aristo, in particular probing how much the LM solvers go beyond simple pattern matching, and what kinds of errors still occur. Finally, I will speculate on the larger quest towards knowledgeable machines that can reason, explain, and interact, and what additional capabilities are needed to reach this broader goal.

[Talk slides]

发言人详细信息

Peter Clark is a Senior Research Manager and founding member of AI2, and has led Project Aristo since its inception in 2014. His research focuses upon natural language processing, machine inference, and commonsense reasoning, and the interplay between these three areas.

专题：
Microsoft Research Talks
日期：
演讲者：
Peter Clark
所属机构：
Allen Institute for AI

系列： Microsoft Research Talks